changelog

fix image upscale on cpu

.eslintrc.js

@@ -78,6 +78,8 @@ module.exports = {
         //extraNetworks.js
         requestGet: "readonly",
         popup: "readonly",
+        // profilerVisualization.js
+        createVisualizationTable: "readonly",
         // from python
         localization: "readonly",
         // progrssbar.js
@@ -86,8 +88,6 @@ module.exports = {
         // imageviewer.js
         modalPrevImage: "readonly",
         modalNextImage: "readonly",
-        // token-counters.js
-        setupTokenCounters: "readonly",
         // localStorage.js
         localSet: "readonly",
         localGet: "readonly",

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -91,7 +91,7 @@ body:
     id: logs
     attributes:
       label: Console logs
-      description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after the bug occured. If it's very long, provide a link to pastebin or similar service.
+      description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after the bug occurred. If it's very long, provide a link to pastebin or similar service.
       render: Shell
     validations:
       required: true

.github/workflows/on_pull_request.yaml

@@ -11,8 +11,8 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+        uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: 3.11
           # NB: there's no cache: pip here since we're not installing anything
@@ -20,7 +20,7 @@ jobs:
           #     not to have GHA download an (at the time of writing) 4 GB cache
           #     of PyTorch and other dependencies.
       - name: Install Ruff
-        run: pip install ruff==0.1.6
+        run: pip install ruff==0.3.3
       - name: Run Ruff
         run: ruff .
   lint-js:
@@ -29,9 +29,9 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Install Node.js
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 18
       - run: npm i --ci

.github/workflows/run_tests.yaml

@@ -11,15 +11,21 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Set up Python 3.10
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: 3.10.6
           cache: pip
           cache-dependency-path: |
             **/requirements*txt
             launch.py
+      - name: Cache models
+        id: cache-models
+        uses: actions/cache@v4
+        with:
+          path: models
+          key: "2023-12-30"
       - name: Install test dependencies
         run: pip install wait-for-it -r requirements-test.txt
         env:
@@ -33,6 +39,8 @@ jobs:
           TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
           WEBUI_LAUNCH_LIVE_OUTPUT: "1"
           PYTHONUNBUFFERED: "1"
+      - name: Print installed packages
+        run: pip freeze
       - name: Start test server
         run: >
           python -m coverage run
@@ -49,7 +57,7 @@ jobs:
           2>&1 | tee output.txt &
       - name: Run tests
         run: |
-          wait-for-it --service 127.0.0.1:7860 -t 600
+          wait-for-it --service 127.0.0.1:7860 -t 20
           python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test
       - name: Kill test server
         if: always()
@@ -60,13 +68,13 @@ jobs:
           python -m coverage report -i
           python -m coverage html -i
       - name: Upload main app output
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         if: always()
         with:
           name: output
           path: output.txt
       - name: Upload coverage HTML
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         if: always()
         with:
           name: htmlcov

.gitignore

@@ -2,6 +2,7 @@ __pycache__
 *.ckpt
 *.safetensors
 *.pth
+.DS_Store
 /ESRGAN/*
 /SwinIR/*
 /repositories
@@ -37,3 +38,7 @@ notification.mp3
 /node_modules
 /package-lock.json
 /.coverage*
+/test/test_outputs
+/cache
+trace.json
+/sysinfo-????-??-??-??-??.json

CHANGELOG.md

@@ -1,3 +1,413 @@
+## 1.10.1
+
+### Bug Fixes:
+* fix image upscale on cpu ([#16275](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16275))
+
+
+## 1.10.0
+
+### Features:
+* A lot of performance improvements (see below in Performance section)
+* Stable Diffusion 3 support ([#16030](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16030), [#16164](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16164), [#16212](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16212))
+  * Recommended Euler sampler; DDIM and other timestamp samplers currently not supported
+  * T5 text model is disabled by default, enable it in settings
+* New schedulers:
+  * Align Your Steps ([#15751](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15751))
+  * KL Optimal ([#15608](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15608))
+  * Normal ([#16149](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16149))
+  * DDIM ([#16149](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16149))
+  * Simple ([#16142](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16142))
+  * Beta ([#16235](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16235))
+* New sampler: DDIM CFG++ ([#16035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16035))
+
+### Minor:
+* Option to skip CFG on early steps ([#15607](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15607))
+* Add --models-dir option ([#15742](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15742))
+* Allow mobile users to open context menu by using two fingers press ([#15682](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15682))
+* Infotext: add Lora name as TI hashes for bundled Textual Inversion ([#15679](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15679))
+* Check model's hash after downloading it to prevent corruped downloads ([#15602](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15602))
+* More extension tag filtering options ([#15627](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15627))
+* When saving AVIF, use JPEG's quality setting ([#15610](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15610))
+* Add filename pattern: `[basename]` ([#15978](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15978))
+* Add option to enable clip skip for clip L on SDXL ([#15992](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15992))
+* Option to prevent screen sleep during generation ([#16001](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16001))
+* ToggleLivePriview button in image viewer ([#16065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16065))
+* Remove ui flashing on reloading and fast scrollong ([#16153](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16153))
+* option to disable save button log.csv ([#16242](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16242))
+
+### Extensions and API:
+* Add process_before_every_sampling hook ([#15984](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15984))
+* Return HTTP 400 instead of 404 on invalid sampler error ([#16140](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16140))
+
+### Performance:
+* [Performance 1/6] use_checkpoint = False ([#15803](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15803))
+* [Performance 2/6] Replace einops.rearrange with torch native ops ([#15804](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15804))
+* [Performance 4/6] Precompute is_sdxl_inpaint flag ([#15806](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15806))
+* [Performance 5/6] Prevent unnecessary extra networks bias backup ([#15816](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15816))
+* [Performance 6/6] Add --precision half option to avoid casting during inference ([#15820](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15820))
+* [Performance] LDM optimization patches ([#15824](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15824))
+* [Performance] Keep sigmas on CPU ([#15823](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15823))
+* Check for nans in unet only once, after all steps have been completed
+* Added pption to run torch profiler for image generation
+
+### Bug Fixes:
+* Fix for grids without comprehensive infotexts ([#15958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15958))
+* feat: lora partial update precede full update ([#15943](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15943))
+* Fix bug where file extension had an extra '.' under some circumstances ([#15893](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15893))
+* Fix corrupt model initial load loop ([#15600](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15600))
+* Allow old sampler names in API ([#15656](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15656))
+* more old sampler scheduler compatibility ([#15681](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15681))
+* Fix Hypertile xyz ([#15831](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15831))
+* XYZ CSV skipinitialspace ([#15832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15832))
+* fix soft inpainting on mps and xpu, torch_utils.float64 ([#15815](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15815))
+* fix extention update when not on main branch ([#15797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15797))
+* update pickle safe filenames
+* use relative path for webui-assets css ([#15757](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15757))
+* When creating a virtual environment, upgrade pip in webui.bat/webui.sh ([#15750](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15750))
+* Fix AttributeError ([#15738](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15738))
+* use script_path for webui root in launch_utils ([#15705](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15705))
+* fix extra batch mode P Transparency ([#15664](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15664))
+* use gradio theme colors in css ([#15680](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15680))
+* Fix dragging text within prompt input ([#15657](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15657))
+* Add correct mimetype for .mjs files ([#15654](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15654))
+* QOL Items - handle metadata issues more cleanly for SD models, Loras and embeddings ([#15632](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15632))
+* replace wsl-open with wslpath and explorer.exe ([#15968](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15968))
+* Fix SDXL Inpaint ([#15976](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15976))
+* multi size grid ([#15988](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15988))
+* fix Replace preview ([#16118](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16118))
+* Possible fix of wrong scale in weight decomposition ([#16151](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16151))
+* Ensure use of python from venv on Mac and Linux ([#16116](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16116))
+* Prioritize python3.10 over python3 if both are available on Linux and Mac (with fallback) ([#16092](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16092))
+* stoping generation extras ([#16085](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16085))
+* Fix SD2 loading ([#16078](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16078), [#16079](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16079))
+* fix infotext Lora hashes for hires fix different lora ([#16062](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16062))
+* Fix sampler scheduler autocorrection warning ([#16054](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16054))
+* fix ui flashing on reloading and fast scrollong ([#16153](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16153))
+* fix upscale logic ([#16239](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16239))
+* [bug] do not break progressbar on non-job actions (add wrap_gradio_call_no_job) ([#16202](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16202))
+* fix OSError: cannot write mode P as JPEG ([#16194](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16194))
+
+### Other:
+* fix changelog #15883 -> #15882 ([#15907](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15907))
+* ReloadUI backgroundColor --background-fill-primary ([#15864](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15864))
+* Use different torch versions for Intel and ARM Macs ([#15851](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15851))
+* XYZ override rework ([#15836](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15836))
+* scroll extensions table on overflow ([#15830](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15830))
+* img2img batch upload method ([#15817](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15817))
+* chore: sync v1.8.0 packages according to changelog ([#15783](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15783))
+* Add AVIF MIME type support to mimetype definitions ([#15739](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15739))
+* Update imageviewer.js ([#15730](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15730))
+* no-referrer ([#15641](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15641))
+* .gitignore trace.json ([#15980](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15980))
+* Bump spandrel to 0.3.4 ([#16144](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16144))
+* Defunct --max-batch-count ([#16119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16119))
+* docs: update bug_report.yml ([#16102](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16102))
+* Maintaining Project Compatibility for Python 3.9 Users Without Upgrade Requirements. ([#16088](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16088), [#16169](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16169), [#16192](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16192))
+* Update torch for ARM Macs to 2.3.1 ([#16059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16059))
+* remove deprecated setting dont_fix_second_order_samplers_schedule ([#16061](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16061))
+* chore: fix typos ([#16060](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16060))
+* shlex.join launch args in console log ([#16170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16170))
+* activate venv .bat ([#16231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16231))
+* add ids to the resize tabs in img2img ([#16218](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16218))
+* update installation guide linux ([#16178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16178))
+* Robust sysinfo ([#16173](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16173))
+* do not send image size on paste inpaint ([#16180](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16180))
+* Fix noisy DS_Store files for MacOS ([#16166](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16166))
+
+
+## 1.9.4
+
+### Bug Fixes:
+*  pin setuptools version to fix the startup error ([#15882](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15882)) 
+
+## 1.9.3
+
+### Bug Fixes:
+*  fix get_crop_region_v2 ([#15594](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15594)) 
+
+## 1.9.2
+
+### Extensions and API:
+* restore 1.8.0-style naming of scripts
+
+## 1.9.1
+
+### Minor:
+* Add avif support ([#15582](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15582))
+* Add filename patterns: `[sampler_scheduler]` and `[scheduler]` ([#15581](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15581))
+
+### Extensions and API:
+* undo adding scripts to sys.modules
+* Add schedulers API endpoint ([#15577](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15577))
+* Remove API upscaling factor limits ([#15560](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15560))
+
+### Bug Fixes:
+* Fix images do not match / Coordinate 'right' is less than 'left' ([#15534](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15534))
+* fix: remove_callbacks_for_function should also remove from the ordered map ([#15533](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15533))
+* fix x1 upscalers ([#15555](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15555))
+* Fix cls.__module__ value in extension script ([#15532](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15532))
+* fix typo in function call (eror -> error) ([#15531](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15531))
+
+### Other:
+* Hide 'No Image data blocks found.' message ([#15567](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15567))
+* Allow webui.sh to be runnable from arbitrary directories containing a .git file ([#15561](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15561))
+* Compatibility with Debian 11, Fedora 34+ and openSUSE 15.4+ ([#15544](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15544))
+* numpy DeprecationWarning product -> prod ([#15547](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15547))
+* get_crop_region_v2 ([#15583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15583), [#15587](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15587))
+
+
+## 1.9.0
+
+### Features:
+* Make refiner switchover based on model timesteps instead of sampling steps ([#14978](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14978))
+* add an option to have old-style directory view instead of tree view; stylistic changes for extra network sorting/search controls
+* add UI for reordering callbacks, support for specifying callback order in extension metadata ([#15205](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15205))
+* Sgm uniform scheduler for SDXL-Lightning models ([#15325](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15325))
+* Scheduler selection in main UI ([#15333](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15333), [#15361](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15361), [#15394](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15394))
+
+### Minor:
+* "open images directory" button now opens the actual dir ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947))
+* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871), [#14973](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14973))
+* make extra network card description plaintext by default, with an option to re-enable HTML as it was
+* resize handle for extra networks ([#15041](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15041))
+* cmd args: `--unix-filenames-sanitization` and `--filenames-max-length` ([#15031](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15031))
+* show extra networks parameters in HTML table rather than raw JSON ([#15131](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15131))
+* Add DoRA (weight-decompose) support for LoRA/LoHa/LoKr ([#15160](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15160), [#15283](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15283))
+* Add '--no-prompt-history' cmd args for disable last generation prompt history ([#15189](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15189))
+* update preview on Replace Preview ([#15201](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15201))
+* only fetch updates for extensions' active git branches ([#15233](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15233))
+* put upscale postprocessing UI into an accordion ([#15223](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15223))
+* Support dragdrop for URLs to read infotext ([#15262](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15262))
+* use diskcache library for caching ([#15287](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15287), [#15299](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15299))
+* Allow PNG-RGBA for Extras Tab ([#15334](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15334))
+* Support cover images embedded in safetensors metadata ([#15319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15319))
+* faster interrupt when using NN upscale ([#15380](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15380))
+* Extras upscaler: an input field to limit maximul side length for the output image ([#15293](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15293), [#15415](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15415), [#15417](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15417), [#15425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15425))
+* add an option to hide postprocessing options in Extras tab
+
+### Extensions and API:
+* ResizeHandleRow - allow overriden column scale parametr ([#15004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15004))
+* call script_callbacks.ui_settings_callback earlier; fix extra-options-section built-in extension killing the ui if using a setting that doesn't exist
+* make it possible to use zoom.js outside webui context ([#15286](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15286), [#15288](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15288))
+* allow variants for extension name in metadata.ini ([#15290](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15290))
+* make reloading UI scripts optional when doing Reload UI, and off by default
+* put request: gr.Request at start of img2img function similar to txt2img
+* open_folder as util ([#15442](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15442))
+* make it possible to import extensions' script files as `import scripts.<filename>` ([#15423](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15423))
+
+### Performance:
+* performance optimization for extra networks HTML pages
+* optimization for extra networks filtering
+* optimization for extra networks sorting
+
+### Bug Fixes:
+* prevent escape button causing an interrupt when no generation has been made yet
+* [bug] avoid doble upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966))
+* possible fix for reload button not appearing in some cases for extra networks.
+* fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006))
+* Fix resize-handle visability for vertical layout (mobile) ([#15010](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15010))
+* register_tmp_file also for mtime ([#15012](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15012))
+* Protect alphas_cumprod during refiner switchover ([#14979](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14979))
+* Fix EXIF orientation in API image loading ([#15062](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15062))
+* Only override emphasis if actually used in prompt ([#15141](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15141))
+* Fix emphasis infotext missing from `params.txt` ([#15142](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15142))
+* fix extract_style_text_from_prompt #15132 ([#15135](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15135))
+* Fix Soft Inpaint for AnimateDiff ([#15148](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15148))
+* edit-attention: deselect surrounding whitespace ([#15178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15178))
+* chore: fix font not loaded ([#15183](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15183))
+* use natural sort in extra networks when ordering by path
+* Fix built-in lora system bugs caused by torch.nn.MultiheadAttention ([#15190](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15190))
+* Avoid error from None in get_learned_conditioning ([#15191](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15191))
+* Add entry to MassFileLister after writing metadata ([#15199](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15199))
+* fix issue with Styles when Hires prompt is used ([#15269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15269), [#15276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15276))
+* Strip comments from hires fix prompt ([#15263](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15263))
+* Make imageviewer event listeners browser consistent ([#15261](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15261))
+* Fix AttributeError in OFT when trying to get MultiheadAttention weight ([#15260](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15260))
+* Add missing .mean() back ([#15239](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15239))
+* fix "Restore progress" button ([#15221](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15221))
+* fix ui-config for InputAccordion [custom_script_source] ([#15231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15231))
+* handle 0 wheel deltaY ([#15268](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15268))
+* prevent alt menu for firefox ([#15267](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15267))
+* fix: fix syntax errors ([#15179](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15179))
+* restore outputs path ([#15307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15307))
+* Escape btn_copy_path filename ([#15316](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15316))
+* Fix extra networks buttons when filename contains an apostrophe ([#15331](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15331))
+* escape brackets in lora random prompt generator ([#15343](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15343))
+* fix: Python version check for PyTorch installation compatibility ([#15390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15390))
+* fix typo in call_queue.py ([#15386](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15386))
+* fix: when find already_loaded model, remove loaded by array index ([#15382](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15382))
+* minor bug fix of sd model memory management ([#15350](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15350))
+* Fix CodeFormer weight ([#15414](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15414))
+* Fix: Remove script callbacks in ordered_callbacks_map ([#15428](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15428))
+* fix limited file write (thanks, Sylwia)
+* Fix extra-single-image API not doing upscale failed ([#15465](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15465))
+* error handling paste_field callables ([#15470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15470))
+
+### Hardware:
+* Add training support and change lspci for Ascend NPU ([#14981](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14981))
+* Update to ROCm5.7 and PyTorch ([#14820](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14820))
+* Better workaround for Navi1, removing --pre for Navi3 ([#15224](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15224))
+* Ascend NPU wiki page ([#15228](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15228))
+
+### Other:
+* Update comment for Pad prompt/negative prompt v0 to add a warning about truncation, make it override the v1 implementation
+* support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002))
+* Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995))
+* Use `absolute` path for normalized filepath ([#15035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15035))
+* resizeHandle handle double tap ([#15065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15065))
+* --dat-models-path cmd flag ([#15039](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15039))
+* Add a direct link to the binary release ([#15059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15059))
+* upscaler_utils: Reduce logging ([#15084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15084))
+* Fix various typos with crate-ci/typos ([#15116](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15116))
+* fix_jpeg_live_preview ([#15102](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15102))
+* [alternative fix] can't load webui if selected wrong extra option in ui ([#15121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15121))
+* Error handling for unsupported transparency ([#14958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14958))
+* Add model description to searched terms ([#15198](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15198))
+* bump action version ([#15272](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15272))
+* PEP 604 annotations ([#15259](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15259))
+* Automatically Set the Scale by value when user selects an Upscale Model ([#15244](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15244))
+* move postprocessing-for-training into builtin extensions ([#15222](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15222))
+* type hinting in shared.py ([#15211](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15211))
+* update ruff to 0.3.3
+* Update pytorch lightning utilities ([#15310](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15310))
+* Add Size as an XYZ Grid option ([#15354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15354))
+* Use HF_ENDPOINT variable for HuggingFace domain with default ([#15443](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15443))
+* re-add update_file_entry ([#15446](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15446))
+* create_infotext allow index and callable, re-work Hires prompt infotext ([#15460](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15460))
+* update restricted_opts to include more options for --hide-ui-dir-config ([#15492](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15492))
+
+
+## 1.8.0
+
+### Features:
+* Update torch to version 2.1.2
+* Soft Inpainting ([#14208](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14208))
+* FP8 support ([#14031](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14031), [#14327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14327))
+* Support for SDXL-Inpaint Model ([#14390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14390))
+* Use Spandrel for upscaling and face restoration architectures ([#14425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14425), [#14467](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14467), [#14473](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14473), [#14474](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14474), [#14477](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14477), [#14476](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14476), [#14484](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14484), [#14500](https://github.com/AUTOMATIC1111/stable-difusion-webui/pull/14500), [#14501](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14501), [#14504](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14504), [#14524](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14524), [#14809](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14809))
+* Automatic backwards version compatibility (when loading infotexts from old images with program version specified, will add compatibility settings)
+* Implement zero terminal SNR noise schedule option (**[SEED BREAKING CHANGE](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Seed-breaking-changes#180-dev-170-225-2024-01-01---zero-terminal-snr-noise-schedule-option)**, [#14145](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14145), [#14979](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14979))
+* Add a [✨] button to run hires fix on selected image in the gallery (with help from [#14598](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14598), [#14626](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14626), [#14728](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14728))
+* [Separate assets repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets); serve fonts locally rather than from google's servers
+* Official LCM Sampler Support ([#14583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14583))
+* Add support for DAT upscaler models ([#14690](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14690), [#15039](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15039))
+* Extra Networks Tree View ([#14588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14588), [#14900](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14900))
+* NPU Support ([#14801](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14801))
+* Prompt comments support
+
+### Minor:
+* Allow pasting in WIDTHxHEIGHT strings into the width/height fields ([#14296](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14296))
+* add option: Live preview in full page image viewer ([#14230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14230), [#14307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14307))
+* Add keyboard shortcuts for generate/skip/interrupt ([#14269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14269))
+* Better TCMALLOC support on different platforms ([#14227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14227), [#14883](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14883), [#14910](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14910))
+* Lora not found warning ([#14464](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14464))
+* Adding negative prompts to Loras in extra networks ([#14475](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14475))
+* xyz_grid: allow varying the seed along an axis separate from axis options ([#12180](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12180))
+* option to convert VAE to bfloat16 (implementation of [#9295](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9295))
+* Better IPEX support ([#14229](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14229), [#14353](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14353), [#14559](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14559), [#14562](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14562), [#14597](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14597))
+* Option to interrupt after current generation rather than immediately ([#13653](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13653), [#14659](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14659))
+* Fullscreen Preview control fading/disable ([#14291](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14291))
+* Finer settings freezing control ([#13789](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13789))
+* Increase Upscaler Limits ([#14589](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14589))
+* Adjust brush size with hotkeys ([#14638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14638))
+* Add checkpoint info to csv log file when saving images ([#14663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14663))
+* Make more columns resizable ([#14740](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14740), [#14884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14884))
+* Add an option to not overlay original image for inpainting for #14727
+* Add Pad conds v0 option to support same generation with DDIM as before 1.6.0
+* Add "Interrupting..." placeholder.
+* Button for refresh extensions list ([#14857](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14857))
+* Add an option to disable normalization after calculating emphasis. ([#14874](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14874))
+* When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior)
+* Configuration for the [📂] button for image gallery ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947))
+* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871), [#14973](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14973))
+* support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002))
+
+### Extensions and API:
+* Removed packages from requirements: basicsr, gfpgan, realesrgan; as well as their dependencies: absl-py, addict, beautifulsoup4, future, gdown, grpcio, importlib-metadata, lmdb, lpips, Markdown, platformdirs, PySocks, soupsieve, tb-nightly, tensorboard-data-server, tomli, Werkzeug, yapf, zipp, soupsieve
+* Enable task ids for API ([#14314](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14314))
+* add override_settings support for infotext API
+* rename generation_parameters_copypaste module to infotext_utils
+* prevent crash due to Script __init__ exception ([#14407](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14407))
+* Bump numpy to 1.26.2 ([#14471](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14471))
+* Add utility to inspect a model's dtype/device ([#14478](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14478))
+* Implement general forward method for all method in built-in lora ext ([#14547](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14547))
+* Execute model_loaded_callback after moving to target device ([#14563](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14563))
+* Add self to CFGDenoiserParams ([#14573](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14573))
+* Allow TLS with API only mode (--nowebui) ([#14593](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14593))
+* New callback: postprocess_image_after_composite ([#14657](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14657))
+* modules/api/api.py: add api endpoint to refresh embeddings list ([#14715](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14715))
+* set_named_arg ([#14773](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14773))
+* add before_token_counter callback and use it for prompt comments
+* ResizeHandleRow - allow overridden column scale parameter ([#15004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15004))
+
+### Performance:
+* Massive performance improvement for extra networks directories with a huge number of files in them in an attempt to tackle #14507 ([#14528](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14528))
+* Reduce unnecessary re-indexing extra networks directory ([#14512](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14512))
+* Avoid unnecessary `isfile`/`exists` calls ([#14527](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14527))
+
+### Bug Fixes:
+* fix multiple bugs related to styles multi-file support ([#14203](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14203), [#14276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14276), [#14707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14707))
+* Lora fixes ([#14300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14300), [#14237](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14237), [#14546](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14546), [#14726](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14726))
+* Re-add setting lost as part of e294e46 ([#14266](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14266))
+* fix extras caption BLIP ([#14330](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14330))
+* include infotext into saved init image for img2img ([#14452](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14452))
+* xyz grid handle axis_type is None ([#14394](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14394))
+* Update Added (Fixed) IPV6 Functionality When there is No Webui Argument Passed webui.py ([#14354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14354))
+* fix API thread safe issues of txt2img and img2img ([#14421](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14421))
+* handle selectable script_index is None ([#14487](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14487))
+* handle config.json failed to load ([#14525](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14525), [#14767](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14767))
+* paste infotext cast int as float ([#14523](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14523))
+* Ensure GRADIO_ANALYTICS_ENABLED is set early enough ([#14537](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14537))
+* Fix logging configuration again ([#14538](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14538))
+* Handle CondFunc exception when resolving attributes ([#14560](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14560))
+* Fix extras big batch crashes ([#14699](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14699))
+* Fix using wrong model caused by alias ([#14655](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14655))
+* Add # to the invalid_filename_chars list ([#14640](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14640))
+* Fix extension check for requirements ([#14639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14639))
+* Fix tab indexes are reset after restart UI ([#14637](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14637))
+* Fix nested manual cast ([#14689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14689))
+* Keep postprocessing upscale selected tab after restart ([#14702](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14702))
+* XYZ grid: filter out blank vals when axis is int or float type (like int axis seed) ([#14754](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14754))
+* fix CLIP Interrogator topN regex ([#14775](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14775))
+* Fix dtype error in MHA layer/change dtype checking mechanism for manual cast ([#14791](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14791))
+* catch load style.csv error ([#14814](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14814))
+* fix error when editing extra networks card
+* fix extra networks metadata failing to work properly when you create the .json file with metadata for the first time.
+* util.walk_files extensions case insensitive ([#14879](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14879))
+* if extensions page not loaded, prevent apply ([#14873](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14873))
+* call the right function for token counter in img2img
+* Fix the bugs that search/reload will disappear when using other ExtraNetworks extensions ([#14939](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14939))
+* Gracefully handle mtime read exception from cache ([#14933](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14933))
+* Only trigger interrupt on `Esc` when interrupt button visible ([#14932](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14932))
+* Disable prompt token counters option actually disables token counting rather than just hiding results.
+* avoid double upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966))
+* Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995))
+* fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006))
+* Fix resize-handle for mobile ([#15010](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15010), [#15065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15065))
+
+### Other:
+* Assign id for "extra_options". Replace numeric field with slider. ([#14270](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14270))
+* change state dict comparison to ref compare ([#14216](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14216))
+* Bump torch-rocm to 5.6/5.7 ([#14293](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14293))
+* Base output path off data path ([#14446](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14446))
+* reorder training preprocessing modules in extras tab ([#14367](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14367))
+* Remove `cleanup_models` code ([#14472](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14472))
+* only rewrite ui-config when there is change ([#14352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14352))
+* Fix lint issue from 501993eb ([#14495](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14495))
+* Update README.md ([#14548](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14548))
+* hires button, fix seeds ()
+* Logging: set formatter correctly for fallback logger too ([#14618](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14618))
+* Read generation info from infotexts rather than json for internal needs (save, extract seed from generated pic) ([#14645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14645))
+* improve get_crop_region ([#14709](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14709))
+* Bump safetensors' version to 0.4.2 ([#14782](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14782))
+* add tooltip create_submit_box ([#14803](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14803))
+* extensions tab table row hover highlight ([#14885](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14885))
+* Always add timestamp to displayed image ([#14890](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14890))
+* Added core.filemode=false so doesn't track changes in file permission… ([#14930](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14930))
+* Normalize command-line argument paths ([#14934](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14934), [#15035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15035))
+* Use original App Title in progress bar ([#14916](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14916))
+* register_tmp_file also for mtime ([#15012](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15012))
+
 ## 1.7.0
 
 ### Features:
@@ -40,7 +450,8 @@
 * infotext updates: add option to disregard certain infotext fields, add option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page
 * add FP32 fallback support on sd_vae_approx ([#14046](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046))
 * support XYZ scripts / split hires path from unet ([#14126](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14126))
-* allow use of mutiple styles csv files ([#14125](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14125))
+* allow use of multiple styles csv files ([#14125](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14125))
+* make extra network card description plaintext by default, with an option (Treat card description as HTML) to re-enable HTML as it was (originally by [#13241](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13241))
 
 ### Extensions and API:
 * update gradio to 3.41.2
@@ -176,7 +587,7 @@
  * new samplers: Restart, DPM++ 2M SDE Exponential, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential ([#12300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12300), [#12519](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12519), [#12542](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12542))
  * rework DDIM, PLMS, UniPC to use CFG denoiser same as in k-diffusion samplers:
    * makes all of them work with img2img
-   * makes prompt composition posssible (AND)
+   * makes prompt composition possible (AND)
    * makes them available for SDXL
  * always show extra networks tabs in the UI ([#11808](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11808))
  * use less RAM when creating models ([#11958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11958), [#12599](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12599))
@@ -352,7 +763,7 @@
  * user metadata system for custom networks
  * extended Lora metadata editor: set activation text, default weight, view tags, training info
  * Lora extension rework to include other types of networks (all that were previously handled by LyCORIS extension)
- * show github stars for extenstions
+ * show github stars for extensions
  * img2img batch mode can read extra stuff from png info
  * img2img batch works with subdirectories
  * hotkeys to move prompt elements: alt+left/right
@@ -571,7 +982,7 @@
  * do not wait for Stable Diffusion model to load at startup
  * add filename patterns: `[denoising]`
  * directory hiding for extra networks: dirs starting with `.` will hide their cards on extra network tabs unless specifically searched for
- * LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metdata of the file, if present, instead of filename (both can be used to activate LoRA)
+ * LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metadata of the file, if present, instead of filename (both can be used to activate LoRA)
  * LoRA: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
  * LoRA: fix some LoRAs not working (ones that have 3x3 convolution layer)
  * LoRA: add an option to use old method of applying LoRAs (producing same results as with kohya-ss)
@@ -601,7 +1012,7 @@
  * fix gamepad navigation
  * make the lightbox fullscreen image function properly
  * fix squished thumbnails in extras tab
- * keep "search" filter for extra networks when user refreshes the tab (previously it showed everthing after you refreshed)
+ * keep "search" filter for extra networks when user refreshes the tab (previously it showed everything after you refreshed)
  * fix webui showing the same image if you configure the generation to always save results into same file
  * fix bug with upscalers not working properly
  * fix MPS on PyTorch 2.0.1, Intel Macs
@@ -619,7 +1030,7 @@
  * switch to PyTorch 2.0.0 (except for AMD GPUs)
  * visual improvements to custom code scripts
  * add filename patterns: `[clip_skip]`, `[hasprompt<>]`, `[batch_number]`, `[generation_number]`
- * add support for saving init images in img2img, and record their hashes in infotext for reproducability
+ * add support for saving init images in img2img, and record their hashes in infotext for reproducibility
  * automatically select current word when adjusting weight with ctrl+up/down
  * add dropdowns for X/Y/Z plot
  * add setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs

README.md

@@ -1,5 +1,5 @@
 # Stable Diffusion web UI
-A browser interface based on Gradio library for Stable Diffusion.
+A web interface for Stable Diffusion, implemented using Gradio library.
 
 ![](screenshot.png)
 
@@ -78,7 +78,7 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Clip skip
 - Hypernetworks
 - Loras (same as Hypernetworks but more pretty)
-- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt 
+- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
 - Can select to load a different VAE from settings screen
 - Estimated completion time in progress bar
 - API
@@ -98,6 +98,7 @@ Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-di
 - [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended)
 - [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
 - [Intel CPUs, Intel GPUs (both integrated and discrete)](https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon) (external wiki page)
+- [Ascend NPUs](https://github.com/wangshuai09/stable-diffusion-webui/wiki/Install-and-run-on-Ascend-NPUs) (external wiki page)
 
 Alternatively, use online services (like Google Colab):
 
@@ -121,16 +122,38 @@ Alternatively, use online services (like Google Colab):
 # Debian-based:
 sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
 # Red Hat-based:
-sudo dnf install wget git python3 gperftools-libs libglvnd-glx 
+sudo dnf install wget git python3 gperftools-libs libglvnd-glx
 # openSUSE-based:
 sudo zypper install wget git python3 libtcmalloc4 libglvnd
 # Arch-based:
 sudo pacman -S wget git python3
 ```
+If your system is very new, you need to install python3.11 or python3.10:
+```bash
+# Ubuntu 24.04
+sudo add-apt-repository ppa:deadsnakes/ppa
+sudo apt update
+sudo apt install python3.11
+
+# Manjaro/Arch
+sudo pacman -S yay
+yay -S python311 # do not confuse with python3.11 package
+
+# Only for 3.11
+# Then set up env variable in launch script
+export python_cmd="python3.11"
+# or in webui-user.sh
+python_cmd="python3.11"
+```
 2. Navigate to the directory you would like the webui to be installed and execute the following command:
 ```bash
 wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
 ```
+Or just clone the repo wherever you want:
+```bash
+git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
+```
+
 3. Run `webui.sh`.
 4. Check `webui-user.sh` for options.
 ### Installation on Apple Silicon
@@ -149,13 +172,14 @@ For the purposes of getting Google and other search engines to crawl the wiki, h
 ## Credits
 Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
 
-- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers
+- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers, https://github.com/mcmonkey4eva/sd3-ref
 - k-diffusion - https://github.com/crowsonkb/k-diffusion.git
-- GFPGAN - https://github.com/TencentARC/GFPGAN.git
-- CodeFormer - https://github.com/sczhou/CodeFormer
-- ESRGAN - https://github.com/xinntao/ESRGAN
-- SwinIR - https://github.com/JingyunLiang/SwinIR
-- Swin2SR - https://github.com/mv-lab/swin2sr
+- Spandrel - https://github.com/chaiNNer-org/spandrel implementing
+  - GFPGAN - https://github.com/TencentARC/GFPGAN.git
+  - CodeFormer - https://github.com/sczhou/CodeFormer
+  - ESRGAN - https://github.com/xinntao/ESRGAN
+  - SwinIR - https://github.com/JingyunLiang/SwinIR
+  - Swin2SR - https://github.com/mv-lab/swin2sr
 - LDSR - https://github.com/Hafiidz/latent-diffusion
 - MiDaS - https://github.com/isl-org/MiDaS
 - Ideas for optimizations - https://github.com/basujindal/stable-diffusion

_typos.toml

@@ -0,0 +1,5 @@
+[default.extend-words]
+# Part of "RGBa" (Pillow's pre-multiplied alpha RGB mode)
+Ba = "Ba"
+# HSA is something AMD uses for their GPUs
+HSA = "HSA"

configs/alt-diffusion-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/alt-diffusion-m18-inference.yaml

@@ -41,7 +41,7 @@ model:
         use_linear_in_transformer: True
         transformer_depth: 1
         context_dim: 1024
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/instruct-pix2pix.yaml

@@ -45,7 +45,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/sd3-inference.yaml

@@ -0,0 +1,5 @@
+model:
+  target: modules.models.sd3.sd3_model.SD3Inferencer
+  params:
+    shift: 3
+    state_dict: null

configs/sd_xl_inpaint.yaml

@@ -0,0 +1,98 @@
+model:
+  target: sgm.models.diffusion.DiffusionEngine
+  params:
+    scale_factor: 0.13025
+    disable_first_stage_autocast: True
+
+    denoiser_config:
+      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
+      params:
+        num_idx: 1000
+
+        weighting_config:
+          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
+        scaling_config:
+          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
+        discretization_config:
+          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
+
+    network_config:
+      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        adm_in_channels: 2816
+        num_classes: sequential
+        use_checkpoint: False
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [4, 2]
+        num_res_blocks: 2
+        channel_mult: [1, 2, 4]
+        num_head_channels: 64
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
+        context_dim: 2048
+        spatial_transformer_attn_type: softmax-xformers
+        legacy: False
+
+    conditioner_config:
+      target: sgm.modules.GeneralConditioner
+      params:
+        emb_models:
+          # crossattn cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
+            params:
+              layer: hidden
+              layer_idx: 11
+          # crossattn and vector cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
+            params:
+              arch: ViT-bigG-14
+              version: laion2b_s39b_b160k
+              freeze: True
+              layer: penultimate
+              always_return_pooled: True
+              legacy: False
+          # vector cond
+          - is_trainable: False
+            input_key: original_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: crop_coords_top_left
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: target_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+
+    first_stage_config:
+      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          attn_type: vanilla-xformers
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult: [1, 2, 4, 4]
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity

configs/v1-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/v1-inpainting-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

extensions-builtin/LDSR/sd_hijack_ddpm_v1.py

@@ -301,7 +301,7 @@ class DDPMV1(pl.LightningModule):
         elif self.parameterization == "x0":
             target = x_start
         else:
-            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+            raise NotImplementedError(f"Parameterization {self.parameterization} not yet supported")
 
         loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
 
@@ -572,7 +572,7 @@ class LatentDiffusionV1(DDPMV1):
         :param h: height
         :param w: width
         :return: normalized distance to image border,
-         wtith min distance = 0 at border and max dist = 0.5 at image center
+         with min distance = 0 at border and max dist = 0.5 at image center
         """
         lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
         arr = self.meshgrid(h, w) / lower_right_corner
@@ -880,7 +880,7 @@ class LatentDiffusionV1(DDPMV1):
     def apply_model(self, x_noisy, t, cond, return_ids=False):
 
         if isinstance(cond, dict):
-            # hybrid case, cond is exptected to be a dict
+            # hybrid case, cond is expected to be a dict
             pass
         else:
             if not isinstance(cond, list):
@@ -916,7 +916,7 @@ class LatentDiffusionV1(DDPMV1):
                 cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
 
             elif self.cond_stage_key == 'coordinates_bbox':
-                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+                assert 'original_image_size' in self.split_input_params, 'BoundingBoxRescaling is missing original_image_size'
 
                 # assuming padding of unfold is always 0 and its dilation is always 1
                 n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
@@ -926,7 +926,7 @@ class LatentDiffusionV1(DDPMV1):
                 num_downs = self.first_stage_model.encoder.num_resolutions - 1
                 rescale_latent = 2 ** (num_downs)
 
-                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # get top left positions of patches as conforming for the bbbox tokenizer, therefore we
                 # need to rescale the tl patch coordinates to be in between (0,1)
                 tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
                                          rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)

extensions-builtin/Lora/extra_networks_lora.py

@@ -9,6 +9,8 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
         self.errors = {}
         """mapping of network names to the number of errors the network had during operation"""
 
+    remove_symbols = str.maketrans('', '', ":,")
+
     def activate(self, p, params_list):
         additional = shared.opts.sd_lora
 
@@ -43,22 +45,15 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
         networks.load_networks(names, te_multipliers, unet_multipliers, dyn_dims)
 
         if shared.opts.lora_add_hashes_to_infotext:
-            network_hashes = []
+            if not getattr(p, "is_hr_pass", False) or not hasattr(p, "lora_hashes"):
+                p.lora_hashes = {}
+
             for item in networks.loaded_networks:
-                shorthash = item.network_on_disk.shorthash
-                if not shorthash:
-                    continue
+                if item.network_on_disk.shorthash and item.mentioned_name:
+                    p.lora_hashes[item.mentioned_name.translate(self.remove_symbols)] = item.network_on_disk.shorthash
 
-                alias = item.mentioned_name
-                if not alias:
-                    continue
-
-                alias = alias.replace(":", "").replace(",", "")
-
-                network_hashes.append(f"{alias}: {shorthash}")
-
-            if network_hashes:
-                p.extra_generation_params["Lora hashes"] = ", ".join(network_hashes)
+            if p.lora_hashes:
+                p.extra_generation_params["Lora hashes"] = ', '.join(f'{k}: {v}' for k, v in p.lora_hashes.items())
 
     def deactivate(self, p):
         if self.errors:

extensions-builtin/Lora/lyco_helpers.py

@@ -30,7 +30,7 @@ def factorization(dimension: int, factor:int=-1) -> tuple[int, int]:
     In LoRA with Kroneckor Product, first value is a value for weight scale.
     secon value is a value for weight.
 
-    Becuase of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
+    Because of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
 
     examples)
     factor

extensions-builtin/Lora/network.py

@@ -3,7 +3,11 @@ import os
 from collections import namedtuple
 import enum
 
+import torch.nn as nn
+import torch.nn.functional as F
+
 from modules import sd_models, cache, errors, hashes, shared
+import modules.models.sd3.mmdit
 
 NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
 
@@ -26,7 +30,6 @@ class NetworkOnDisk:
 
         def read_metadata():
             metadata = sd_models.read_metadata_from_safetensors(filename)
-            metadata.pop('ssmd_cover_images', None)  # those are cover images, and they are too big to display in UI as text
 
             return metadata
 
@@ -112,14 +115,49 @@ class NetworkModule:
         self.sd_key = weights.sd_key
         self.sd_module = weights.sd_module
 
-        if hasattr(self.sd_module, 'weight'):
+        if isinstance(self.sd_module, modules.models.sd3.mmdit.QkvLinear):
+            s = self.sd_module.weight.shape
+            self.shape = (s[0] // 3, s[1])
+        elif hasattr(self.sd_module, 'weight'):
             self.shape = self.sd_module.weight.shape
+        elif isinstance(self.sd_module, nn.MultiheadAttention):
+            # For now, only self-attn use Pytorch's MHA
+            # So assume all qkvo proj have same shape
+            self.shape = self.sd_module.out_proj.weight.shape
+        else:
+            self.shape = None
+
+        self.ops = None
+        self.extra_kwargs = {}
+        if isinstance(self.sd_module, nn.Conv2d):
+            self.ops = F.conv2d
+            self.extra_kwargs = {
+                'stride': self.sd_module.stride,
+                'padding': self.sd_module.padding
+            }
+        elif isinstance(self.sd_module, nn.Linear):
+            self.ops = F.linear
+        elif isinstance(self.sd_module, nn.LayerNorm):
+            self.ops = F.layer_norm
+            self.extra_kwargs = {
+                'normalized_shape': self.sd_module.normalized_shape,
+                'eps': self.sd_module.eps
+            }
+        elif isinstance(self.sd_module, nn.GroupNorm):
+            self.ops = F.group_norm
+            self.extra_kwargs = {
+                'num_groups': self.sd_module.num_groups,
+                'eps': self.sd_module.eps
+            }
 
         self.dim = None
         self.bias = weights.w.get("bias")
         self.alpha = weights.w["alpha"].item() if "alpha" in weights.w else None
         self.scale = weights.w["scale"].item() if "scale" in weights.w else None
 
+        self.dora_scale = weights.w.get("dora_scale", None)
+        self.dora_norm_dims = len(self.shape) - 1
+
     def multiplier(self):
         if 'transformer' in self.sd_key[:20]:
             return self.network.te_multiplier
@@ -134,10 +172,31 @@ class NetworkModule:
 
         return 1.0
 
+    def apply_weight_decompose(self, updown, orig_weight):
+        # Match the device/dtype
+        orig_weight = orig_weight.to(updown.dtype)
+        dora_scale = self.dora_scale.to(device=orig_weight.device, dtype=updown.dtype)
+        updown = updown.to(orig_weight.device)
+
+        merged_scale1 = updown + orig_weight
+        merged_scale1_norm = (
+            merged_scale1.transpose(0, 1)
+            .reshape(merged_scale1.shape[1], -1)
+            .norm(dim=1, keepdim=True)
+            .reshape(merged_scale1.shape[1], *[1] * self.dora_norm_dims)
+            .transpose(0, 1)
+        )
+
+        dora_merged = (
+            merged_scale1 * (dora_scale / merged_scale1_norm)
+        )
+        final_updown = dora_merged - orig_weight
+        return final_updown
+
     def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
         if self.bias is not None:
             updown = updown.reshape(self.bias.shape)
-            updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
+            updown += self.bias.to(orig_weight.device, dtype=updown.dtype)
             updown = updown.reshape(output_shape)
 
         if len(output_shape) == 4:
@@ -149,11 +208,21 @@ class NetworkModule:
         if ex_bias is not None:
             ex_bias = ex_bias * self.multiplier()
 
-        return updown * self.calc_scale() * self.multiplier(), ex_bias
+        updown = updown * self.calc_scale()
+
+        if self.dora_scale is not None:
+            updown = self.apply_weight_decompose(updown, orig_weight)
+
+        return updown * self.multiplier(), ex_bias
 
     def calc_updown(self, target):
         raise NotImplementedError()
 
     def forward(self, x, y):
-        raise NotImplementedError()
+        """A general forward implementation for all modules"""
+        if self.ops is None:
+            raise NotImplementedError()
+        else:
+            updown, ex_bias = self.calc_updown(self.sd_module.weight)
+            return y + self.ops(x, weight=updown, bias=ex_bias, **self.extra_kwargs)
 

extensions-builtin/Lora/network_full.py

@@ -18,9 +18,9 @@ class NetworkModuleFull(network.NetworkModule):
 
     def calc_updown(self, orig_weight):
         output_shape = self.weight.shape
-        updown = self.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+        updown = self.weight.to(orig_weight.device)
         if self.ex_bias is not None:
-            ex_bias = self.ex_bias.to(orig_weight.device, dtype=orig_weight.dtype)
+            ex_bias = self.ex_bias.to(orig_weight.device)
         else:
             ex_bias = None
 

extensions-builtin/Lora/network_glora.py

@@ -22,12 +22,12 @@ class NetworkModuleGLora(network.NetworkModule):
         self.w2b = weights.w["b2.weight"]
 
     def calc_updown(self, orig_weight):
-        w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+        w1a = self.w1a.to(orig_weight.device)
+        w1b = self.w1b.to(orig_weight.device)
+        w2a = self.w2a.to(orig_weight.device)
+        w2b = self.w2b.to(orig_weight.device)
 
         output_shape = [w1a.size(0), w1b.size(1)]
-        updown = ((w2b @ w1b) + ((orig_weight @ w2a) @ w1a))
+        updown = ((w2b @ w1b) + ((orig_weight.to(dtype = w1a.dtype) @ w2a) @ w1a))
 
         return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_hada.py

@@ -27,16 +27,16 @@ class NetworkModuleHada(network.NetworkModule):
         self.t2 = weights.w.get("hada_t2")
 
     def calc_updown(self, orig_weight):
-        w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+        w1a = self.w1a.to(orig_weight.device)
+        w1b = self.w1b.to(orig_weight.device)
+        w2a = self.w2a.to(orig_weight.device)
+        w2b = self.w2b.to(orig_weight.device)
 
         output_shape = [w1a.size(0), w1b.size(1)]
 
         if self.t1 is not None:
             output_shape = [w1a.size(1), w1b.size(1)]
-            t1 = self.t1.to(orig_weight.device, dtype=orig_weight.dtype)
+            t1 = self.t1.to(orig_weight.device)
             updown1 = lyco_helpers.make_weight_cp(t1, w1a, w1b)
             output_shape += t1.shape[2:]
         else:
@@ -45,7 +45,7 @@ class NetworkModuleHada(network.NetworkModule):
             updown1 = lyco_helpers.rebuild_conventional(w1a, w1b, output_shape)
 
         if self.t2 is not None:
-            t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
+            t2 = self.t2.to(orig_weight.device)
             updown2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
         else:
             updown2 = lyco_helpers.rebuild_conventional(w2a, w2b, output_shape)

extensions-builtin/Lora/network_ia3.py

@@ -17,7 +17,7 @@ class NetworkModuleIa3(network.NetworkModule):
         self.on_input = weights.w["on_input"].item()
 
     def calc_updown(self, orig_weight):
-        w = self.w.to(orig_weight.device, dtype=orig_weight.dtype)
+        w = self.w.to(orig_weight.device)
 
         output_shape = [w.size(0), orig_weight.size(1)]
         if self.on_input:

extensions-builtin/Lora/network_lokr.py

@@ -37,22 +37,22 @@ class NetworkModuleLokr(network.NetworkModule):
 
     def calc_updown(self, orig_weight):
         if self.w1 is not None:
-            w1 = self.w1.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1 = self.w1.to(orig_weight.device)
         else:
-            w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
-            w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1a = self.w1a.to(orig_weight.device)
+            w1b = self.w1b.to(orig_weight.device)
             w1 = w1a @ w1b
 
         if self.w2 is not None:
-            w2 = self.w2.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2 = self.w2.to(orig_weight.device)
         elif self.t2 is None:
-            w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-            w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2a = self.w2a.to(orig_weight.device)
+            w2b = self.w2b.to(orig_weight.device)
             w2 = w2a @ w2b
         else:
-            t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
-            w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-            w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+            t2 = self.t2.to(orig_weight.device)
+            w2a = self.w2a.to(orig_weight.device)
+            w2b = self.w2b.to(orig_weight.device)
             w2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
 
         output_shape = [w1.size(0) * w2.size(0), w1.size(1) * w2.size(1)]

extensions-builtin/Lora/network_lora.py

@@ -1,6 +1,7 @@
 import torch
 
 import lyco_helpers
+import modules.models.sd3.mmdit
 import network
 from modules import devices
 
@@ -10,6 +11,13 @@ class ModuleTypeLora(network.ModuleType):
         if all(x in weights.w for x in ["lora_up.weight", "lora_down.weight"]):
             return NetworkModuleLora(net, weights)
 
+        if all(x in weights.w for x in ["lora_A.weight", "lora_B.weight"]):
+            w = weights.w.copy()
+            weights.w.clear()
+            weights.w.update({"lora_up.weight": w["lora_B.weight"], "lora_down.weight": w["lora_A.weight"]})
+
+            return NetworkModuleLora(net, weights)
+
         return None
 
 
@@ -29,7 +37,7 @@ class NetworkModuleLora(network.NetworkModule):
         if weight is None and none_ok:
             return None
 
-        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention]
+        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention, modules.models.sd3.mmdit.QkvLinear]
         is_conv = type(self.sd_module) in [torch.nn.Conv2d]
 
         if is_linear:
@@ -61,13 +69,13 @@ class NetworkModuleLora(network.NetworkModule):
         return module
 
     def calc_updown(self, orig_weight):
-        up = self.up_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
-        down = self.down_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+        up = self.up_model.weight.to(orig_weight.device)
+        down = self.down_model.weight.to(orig_weight.device)
 
         output_shape = [up.size(0), down.size(1)]
         if self.mid_model is not None:
             # cp-decomposition
-            mid = self.mid_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+            mid = self.mid_model.weight.to(orig_weight.device)
             updown = lyco_helpers.rebuild_cp_decomposition(up, down, mid)
             output_shape += mid.shape[2:]
         else:

extensions-builtin/Lora/network_norm.py

@@ -18,10 +18,10 @@ class NetworkModuleNorm(network.NetworkModule):
 
     def calc_updown(self, orig_weight):
         output_shape = self.w_norm.shape
-        updown = self.w_norm.to(orig_weight.device, dtype=orig_weight.dtype)
+        updown = self.w_norm.to(orig_weight.device)
 
         if self.b_norm is not None:
-            ex_bias = self.b_norm.to(orig_weight.device, dtype=orig_weight.dtype)
+            ex_bias = self.b_norm.to(orig_weight.device)
         else:
             ex_bias = None
 

extensions-builtin/Lora/network_oft.py

@@ -1,6 +1,5 @@
 import torch
 import network
-from lyco_helpers import factorization
 from einops import rearrange
 
 
@@ -21,15 +20,18 @@ class NetworkModuleOFT(network.NetworkModule):
         self.lin_module = None
         self.org_module: list[torch.Module] = [self.sd_module]
 
-        # kohya-ss
+        self.scale = 1.0
+        self.is_R = False
+        self.is_boft = False
+
+        # kohya-ss/New LyCORIS OFT/BOFT
         if "oft_blocks" in weights.w.keys():
-            self.is_kohya = True
             self.oft_blocks = weights.w["oft_blocks"] # (num_blocks, block_size, block_size)
-            self.alpha = weights.w["alpha"] # alpha is constraint
+            self.alpha = weights.w.get("alpha", None) # alpha is constraint
             self.dim = self.oft_blocks.shape[0] # lora dim
-        # LyCORIS
+        # Old LyCORIS OFT
         elif "oft_diag" in weights.w.keys():
-            self.is_kohya = False
+            self.is_R = True
             self.oft_blocks = weights.w["oft_diag"]
             # self.alpha is unused
             self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size)
@@ -45,53 +47,72 @@ class NetworkModuleOFT(network.NetworkModule):
         elif is_other_linear:
             self.out_dim = self.sd_module.embed_dim
 
-        if self.is_kohya:
-            self.constraint = self.alpha * self.out_dim
-            self.num_blocks = self.dim
-            self.block_size = self.out_dim // self.dim
-        else:
+        # LyCORIS BOFT
+        if self.oft_blocks.dim() == 4:
+            self.is_boft = True
+        self.rescale = weights.w.get('rescale', None)
+        if self.rescale is not None and not is_other_linear:
+            self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1))
+
+        self.num_blocks = self.dim
+        self.block_size = self.out_dim // self.dim
+        self.constraint = (0 if self.alpha is None else self.alpha) * self.out_dim
+        if self.is_R:
             self.constraint = None
-            self.block_size, self.num_blocks = factorization(self.out_dim, self.dim)
-
-    def calc_updown_kb(self, orig_weight, multiplier):
-        oft_blocks = self.oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
-        oft_blocks = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix
-
-        R = oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
-        R = R * multiplier + torch.eye(self.block_size, device=orig_weight.device)
-
-        # This errors out for MultiheadAttention, might need to be handled up-stream
-        merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
-        merged_weight = torch.einsum(
-            'k n m, k n ... -> k m ...',
-            R,
-            merged_weight
-        )
-        merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...')
-
-        updown = merged_weight.to(orig_weight.device, dtype=orig_weight.dtype) - orig_weight
-        output_shape = orig_weight.shape
-        return self.finalize_updown(updown, orig_weight, output_shape)
+            self.block_size = self.dim
+            self.num_blocks = self.out_dim // self.dim
+        elif self.is_boft:
+            self.boft_m = self.oft_blocks.shape[0]
+            self.num_blocks = self.oft_blocks.shape[1]
+            self.block_size = self.oft_blocks.shape[2]
+            self.boft_b = self.block_size
 
     def calc_updown(self, orig_weight):
-        # if alpha is a very small number as in coft, calc_scale() will return a almost zero number so we ignore it
-        multiplier = self.multiplier()
-        return self.calc_updown_kb(orig_weight, multiplier)
+        oft_blocks = self.oft_blocks.to(orig_weight.device)
+        eye = torch.eye(self.block_size, device=oft_blocks.device)
 
-    # override to remove the multiplier/scale factor; it's already multiplied in get_weight
-    def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
-        if self.bias is not None:
-            updown = updown.reshape(self.bias.shape)
-            updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
-            updown = updown.reshape(output_shape)
+        if not self.is_R:
+            block_Q = oft_blocks - oft_blocks.transpose(-1, -2) # ensure skew-symmetric orthogonal matrix
+            if self.constraint != 0:
+                norm_Q = torch.norm(block_Q.flatten())
+                new_norm_Q = torch.clamp(norm_Q, max=self.constraint.to(oft_blocks.device))
+                block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
+            oft_blocks = torch.matmul(eye + block_Q, (eye - block_Q).float().inverse())
 
-        if len(output_shape) == 4:
-            updown = updown.reshape(output_shape)
+        R = oft_blocks.to(orig_weight.device)
 
-        if orig_weight.size().numel() == updown.size().numel():
-            updown = updown.reshape(orig_weight.shape)
+        if not self.is_boft:
+            # This errors out for MultiheadAttention, might need to be handled up-stream
+            merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
+            merged_weight = torch.einsum(
+                'k n m, k n ... -> k m ...',
+                R,
+                merged_weight
+            )
+            merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...')
+        else:
+            # TODO: determine correct value for scale
+            scale = 1.0
+            m = self.boft_m
+            b = self.boft_b
+            r_b = b // 2
+            inp = orig_weight
+            for i in range(m):
+                bi = R[i] # b_num, b_size, b_size
+                if i == 0:
+                    # Apply multiplier/scale and rescale into first weight
+                    bi = bi * scale + (1 - scale) * eye
+                inp = rearrange(inp, "(c g k) ... -> (c k g) ...", g=2, k=2**i * r_b)
+                inp = rearrange(inp, "(d b) ... -> d b ...", b=b)
+                inp = torch.einsum("b i j, b j ... -> b i ...", bi, inp)
+                inp = rearrange(inp, "d b ... -> (d b) ...")
+                inp = rearrange(inp, "(c k g) ... -> (c g k) ...", g=2, k=2**i * r_b)
+            merged_weight = inp
 
-        if ex_bias is not None:
-            ex_bias = ex_bias * self.multiplier()
+        # Rescale mechanism
+        if self.rescale is not None:
+            merged_weight = self.rescale.to(merged_weight) * merged_weight
 
-        return updown, ex_bias
+        updown = merged_weight.to(orig_weight.device) - orig_weight.to(merged_weight.dtype)
+        output_shape = orig_weight.shape
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/networks.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+import gradio as gr
 import logging
 import os
 import re
@@ -18,6 +20,7 @@ from typing import Union
 
 from modules import shared, devices, sd_models, errors, scripts, sd_hijack
 import modules.textual_inversion.textual_inversion as textual_inversion
+import modules.models.sd3.mmdit
 
 from lora_logger import logger
 
@@ -129,7 +132,9 @@ def assign_network_names_to_compvis_modules(sd_model):
                 network_layer_mapping[network_name] = module
                 module.network_layer_name = network_name
     else:
-        for name, module in shared.sd_model.cond_stage_model.wrapped.named_modules():
+        cond_stage_model = getattr(shared.sd_model.cond_stage_model, 'wrapped', shared.sd_model.cond_stage_model)
+
+        for name, module in cond_stage_model.named_modules():
             network_name = name.replace(".", "_")
             network_layer_mapping[network_name] = module
             module.network_layer_name = network_name
@@ -142,6 +147,14 @@ def assign_network_names_to_compvis_modules(sd_model):
     sd_model.network_layer_mapping = network_layer_mapping
 
 
+class BundledTIHash(str):
+    def __init__(self, hash_str):
+        self.hash = hash_str
+
+    def __str__(self):
+        return self.hash if shared.opts.lora_bundled_ti_to_infotext else ''
+
+
 def load_network(name, network_on_disk):
     net = network.Network(name, network_on_disk)
     net.mtime = os.path.getmtime(network_on_disk.filename)
@@ -154,12 +167,27 @@ def load_network(name, network_on_disk):
 
     keys_failed_to_match = {}
     is_sd2 = 'model_transformer_resblocks' in shared.sd_model.network_layer_mapping
+    if hasattr(shared.sd_model, 'diffusers_weight_map'):
+        diffusers_weight_map = shared.sd_model.diffusers_weight_map
+    elif hasattr(shared.sd_model, 'diffusers_weight_mapping'):
+        diffusers_weight_map = {}
+        for k, v in shared.sd_model.diffusers_weight_mapping():
+            diffusers_weight_map[k] = v
+        shared.sd_model.diffusers_weight_map = diffusers_weight_map
+    else:
+        diffusers_weight_map = None
 
     matched_networks = {}
     bundle_embeddings = {}
 
     for key_network, weight in sd.items():
-        key_network_without_network_parts, network_part = key_network.split(".", 1)
+
+        if diffusers_weight_map:
+            key_network_without_network_parts, network_name, network_weight = key_network.rsplit(".", 2)
+            network_part = network_name + '.' + network_weight
+        else:
+            key_network_without_network_parts, _, network_part = key_network.partition(".")
+
         if key_network_without_network_parts == "bundle_emb":
             emb_name, vec_name = network_part.split(".", 1)
             emb_dict = bundle_embeddings.get(emb_name, {})
@@ -170,7 +198,11 @@ def load_network(name, network_on_disk):
                 emb_dict[vec_name] = weight
             bundle_embeddings[emb_name] = emb_dict
 
-        key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
+        if diffusers_weight_map:
+            key = diffusers_weight_map.get(key_network_without_network_parts, key_network_without_network_parts)
+        else:
+            key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
+
         sd_module = shared.sd_model.network_layer_mapping.get(key, None)
 
         if sd_module is None:
@@ -227,6 +259,7 @@ def load_network(name, network_on_disk):
     for emb_name, data in bundle_embeddings.items():
         embedding = textual_inversion.create_embedding_from_data(data, emb_name, filename=network_on_disk.filename + "/" + emb_name)
         embedding.loaded = None
+        embedding.shorthash = BundledTIHash(name)
         embeddings[emb_name] = embedding
 
     net.bundle_embeddings = embeddings
@@ -258,11 +291,21 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
 
     loaded_networks.clear()
 
-    networks_on_disk = [available_network_aliases.get(name, None) for name in names]
+    unavailable_networks = []
+    for name in names:
+        if name.lower() in forbidden_network_aliases and available_networks.get(name) is None:
+            unavailable_networks.append(name)
+        elif available_network_aliases.get(name) is None:
+            unavailable_networks.append(name)
+
+    if unavailable_networks:
+        update_available_networks_by_names(unavailable_networks)
+
+    networks_on_disk = [available_networks.get(name, None) if name.lower() in forbidden_network_aliases else available_network_aliases.get(name, None) for name in names]
     if any(x is None for x in networks_on_disk):
         list_available_networks()
 
-        networks_on_disk = [available_network_aliases.get(name, None) for name in names]
+        networks_on_disk = [available_networks.get(name, None) if name.lower() in forbidden_network_aliases else available_network_aliases.get(name, None) for name in names]
 
     failed_to_load_networks = []
 
@@ -313,11 +356,38 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
                 emb_db.skipped_embeddings[name] = embedding
 
     if failed_to_load_networks:
-        sd_hijack.model_hijack.comments.append("Networks not found: " + ", ".join(failed_to_load_networks))
+        lora_not_found_message = f'Lora not found: {", ".join(failed_to_load_networks)}'
+        sd_hijack.model_hijack.comments.append(lora_not_found_message)
+        if shared.opts.lora_not_found_warning_console:
+            print(f'\n{lora_not_found_message}\n')
+        if shared.opts.lora_not_found_gradio_warning:
+            gr.Warning(lora_not_found_message)
 
     purge_networks_from_memory()
 
 
+def allowed_layer_without_weight(layer):
+    if isinstance(layer, torch.nn.LayerNorm) and not layer.elementwise_affine:
+        return True
+
+    return False
+
+
+def store_weights_backup(weight):
+    if weight is None:
+        return None
+
+    return weight.to(devices.cpu, copy=True)
+
+
+def restore_weights_backup(obj, field, weight):
+    if weight is None:
+        setattr(obj, field, None)
+        return
+
+    getattr(obj, field).copy_(weight)
+
+
 def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
     weights_backup = getattr(self, "network_weights_backup", None)
     bias_backup = getattr(self, "network_bias_backup", None)
@@ -327,28 +397,22 @@ def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Li
 
     if weights_backup is not None:
         if isinstance(self, torch.nn.MultiheadAttention):
-            self.in_proj_weight.copy_(weights_backup[0])
-            self.out_proj.weight.copy_(weights_backup[1])
+            restore_weights_backup(self, 'in_proj_weight', weights_backup[0])
+            restore_weights_backup(self.out_proj, 'weight', weights_backup[1])
         else:
-            self.weight.copy_(weights_backup)
+            restore_weights_backup(self, 'weight', weights_backup)
 
-    if bias_backup is not None:
-        if isinstance(self, torch.nn.MultiheadAttention):
-            self.out_proj.bias.copy_(bias_backup)
-        else:
-            self.bias.copy_(bias_backup)
+    if isinstance(self, torch.nn.MultiheadAttention):
+        restore_weights_backup(self.out_proj, 'bias', bias_backup)
     else:
-        if isinstance(self, torch.nn.MultiheadAttention):
-            self.out_proj.bias = None
-        else:
-            self.bias = None
+        restore_weights_backup(self, 'bias', bias_backup)
 
 
 def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
     """
     Applies the currently selected set of networks to the weights of torch layer self.
     If weights already have this particular set of networks applied, does nothing.
-    If not, restores orginal weights from backup and alters weights according to networks.
+    If not, restores original weights from backup and alters weights according to networks.
     """
 
     network_layer_name = getattr(self, 'network_layer_name', None)
@@ -360,24 +424,30 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
 
     weights_backup = getattr(self, "network_weights_backup", None)
     if weights_backup is None and wanted_names != ():
-        if current_names != ():
-            raise RuntimeError("no backup weights found and current weights are not unchanged")
+        if current_names != () and not allowed_layer_without_weight(self):
+            raise RuntimeError(f"{network_layer_name} - no backup weights found and current weights are not unchanged")
 
         if isinstance(self, torch.nn.MultiheadAttention):
-            weights_backup = (self.in_proj_weight.to(devices.cpu, copy=True), self.out_proj.weight.to(devices.cpu, copy=True))
+            weights_backup = (store_weights_backup(self.in_proj_weight), store_weights_backup(self.out_proj.weight))
         else:
-            weights_backup = self.weight.to(devices.cpu, copy=True)
+            weights_backup = store_weights_backup(self.weight)
 
         self.network_weights_backup = weights_backup
 
     bias_backup = getattr(self, "network_bias_backup", None)
-    if bias_backup is None:
+    if bias_backup is None and wanted_names != ():
         if isinstance(self, torch.nn.MultiheadAttention) and self.out_proj.bias is not None:
-            bias_backup = self.out_proj.bias.to(devices.cpu, copy=True)
+            bias_backup = store_weights_backup(self.out_proj.bias)
         elif getattr(self, 'bias', None) is not None:
-            bias_backup = self.bias.to(devices.cpu, copy=True)
+            bias_backup = store_weights_backup(self.bias)
         else:
             bias_backup = None
+
+        # Unlike weight which always has value, some modules don't have bias.
+        # Only report if bias is not None and current bias are not unchanged.
+        if bias_backup is not None and current_names != ():
+            raise RuntimeError("no backup bias found and current bias are not unchanged")
+
         self.network_bias_backup = bias_backup
 
     if current_names != wanted_names:
@@ -385,21 +455,29 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
 
         for net in loaded_networks:
             module = net.modules.get(network_layer_name, None)
-            if module is not None and hasattr(self, 'weight'):
+            if module is not None and hasattr(self, 'weight') and not isinstance(module, modules.models.sd3.mmdit.QkvLinear):
                 try:
                     with torch.no_grad():
-                        updown, ex_bias = module.calc_updown(self.weight)
+                        if getattr(self, 'fp16_weight', None) is None:
+                            weight = self.weight
+                            bias = self.bias
+                        else:
+                            weight = self.fp16_weight.clone().to(self.weight.device)
+                            bias = getattr(self, 'fp16_bias', None)
+                            if bias is not None:
+                                bias = bias.clone().to(self.bias.device)
+                        updown, ex_bias = module.calc_updown(weight)
 
-                        if len(self.weight.shape) == 4 and self.weight.shape[1] == 9:
+                        if len(weight.shape) == 4 and weight.shape[1] == 9:
                             # inpainting model. zero pad updown to make channel[1]  4 to 9
                             updown = torch.nn.functional.pad(updown, (0, 0, 0, 0, 0, 5))
 
-                        self.weight += updown
+                        self.weight.copy_((weight.to(dtype=updown.dtype) + updown).to(dtype=self.weight.dtype))
                         if ex_bias is not None and hasattr(self, 'bias'):
                             if self.bias is None:
-                                self.bias = torch.nn.Parameter(ex_bias)
+                                self.bias = torch.nn.Parameter(ex_bias).to(self.weight.dtype)
                             else:
-                                self.bias += ex_bias
+                                self.bias.copy_((bias + ex_bias).to(dtype=self.bias.dtype))
                 except RuntimeError as e:
                     logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
                     extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
@@ -414,9 +492,12 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
             if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
                 try:
                     with torch.no_grad():
-                        updown_q, _ = module_q.calc_updown(self.in_proj_weight)
-                        updown_k, _ = module_k.calc_updown(self.in_proj_weight)
-                        updown_v, _ = module_v.calc_updown(self.in_proj_weight)
+                        # Send "real" orig_weight into MHA's lora module
+                        qw, kw, vw = self.in_proj_weight.chunk(3, 0)
+                        updown_q, _ = module_q.calc_updown(qw)
+                        updown_k, _ = module_k.calc_updown(kw)
+                        updown_v, _ = module_v.calc_updown(vw)
+                        del qw, kw, vw
                         updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
                         updown_out, ex_bias = module_out.calc_updown(self.out_proj.weight)
 
@@ -434,6 +515,24 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
 
                 continue
 
+            if isinstance(self, modules.models.sd3.mmdit.QkvLinear) and module_q and module_k and module_v:
+                try:
+                    with torch.no_grad():
+                        # Send "real" orig_weight into MHA's lora module
+                        qw, kw, vw = self.weight.chunk(3, 0)
+                        updown_q, _ = module_q.calc_updown(qw)
+                        updown_k, _ = module_k.calc_updown(kw)
+                        updown_v, _ = module_v.calc_updown(vw)
+                        del qw, kw, vw
+                        updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
+                        self.weight += updown_qkv
+
+                except RuntimeError as e:
+                    logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+                    extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+                continue
+
             if module is None:
                 continue
 
@@ -443,23 +542,23 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
         self.network_current_names = wanted_names
 
 
-def network_forward(module, input, original_forward):
+def network_forward(org_module, input, original_forward):
     """
     Old way of applying Lora by executing operations during layer's forward.
     Stacking many loras this way results in big performance degradation.
     """
 
     if len(loaded_networks) == 0:
-        return original_forward(module, input)
+        return original_forward(org_module, input)
 
     input = devices.cond_cast_unet(input)
 
-    network_restore_weights_from_backup(module)
-    network_reset_cached_weight(module)
+    network_restore_weights_from_backup(org_module)
+    network_reset_cached_weight(org_module)
 
-    y = original_forward(module, input)
+    y = original_forward(org_module, input)
 
-    network_layer_name = getattr(module, 'network_layer_name', None)
+    network_layer_name = getattr(org_module, 'network_layer_name', None)
     for lora in loaded_networks:
         module = lora.modules.get(network_layer_name, None)
         if module is None:
@@ -548,22 +647,16 @@ def network_MultiheadAttention_load_state_dict(self, *args, **kwargs):
     return originals.MultiheadAttention_load_state_dict(self, *args, **kwargs)
 
 
-def list_available_networks():
-    available_networks.clear()
-    available_network_aliases.clear()
-    forbidden_network_aliases.clear()
-    available_network_hash_lookup.clear()
-    forbidden_network_aliases.update({"none": 1, "Addams": 1})
-
-    os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
-
+def process_network_files(names: list[str] | None = None):
     candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
     candidates += list(shared.walk_files(shared.cmd_opts.lyco_dir_backcompat, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
     for filename in candidates:
         if os.path.isdir(filename):
             continue
-
         name = os.path.splitext(os.path.basename(filename))[0]
+        # if names is provided, only load networks with names in the list
+        if names and name not in names:
+            continue
         try:
             entry = network.NetworkOnDisk(name, filename)
         except OSError:  # should catch FileNotFoundError and PermissionError etc.
@@ -579,6 +672,22 @@ def list_available_networks():
         available_network_aliases[entry.alias] = entry
 
 
+def update_available_networks_by_names(names: list[str]):
+    process_network_files(names)
+
+
+def list_available_networks():
+    available_networks.clear()
+    available_network_aliases.clear()
+    forbidden_network_aliases.clear()
+    available_network_hash_lookup.clear()
+    forbidden_network_aliases.update({"none": 1, "Addams": 1})
+
+    os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
+
+    process_network_files()
+
+
 re_network_name = re.compile(r"(.*)\s*\([0-9a-fA-F]+\)")
 
 

extensions-builtin/Lora/preload.py

@@ -1,7 +1,8 @@
 import os
 from modules import paths
+from modules.paths_internal import normalized_filepath
 
 
 def preload(parser):
-    parser.add_argument("--lora-dir", type=str, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
-    parser.add_argument("--lyco-dir-backcompat", type=str, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))
+    parser.add_argument("--lora-dir", type=normalized_filepath, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
+    parser.add_argument("--lyco-dir-backcompat", type=normalized_filepath, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))

extensions-builtin/Lora/scripts/lora_script.py

@@ -36,9 +36,12 @@ shared.options_templates.update(shared.options_section(('extra_networks', "Extra
     "sd_lora": shared.OptionInfo("None", "Add network to prompt", gr.Dropdown, lambda: {"choices": ["None", *networks.available_networks]}, refresh=networks.list_available_networks),
     "lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to Lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
     "lora_add_hashes_to_infotext": shared.OptionInfo(True, "Add Lora hashes to infotext"),
+    "lora_bundled_ti_to_infotext": shared.OptionInfo(True, "Add Lora name as TI hashes for bundled Textual Inversion").info('"Add Textual Inversion hashes to infotext" needs to be enabled'),
     "lora_show_all": shared.OptionInfo(False, "Always show all networks on the Lora page").info("otherwise, those detected as for incompatible version of Stable Diffusion will be hidden"),
     "lora_hide_unknown_for_versions": shared.OptionInfo([], "Hide networks of unknown versions for model versions", gr.CheckboxGroup, {"choices": ["SD1", "SD2", "SDXL"]}),
     "lora_in_memory_limit": shared.OptionInfo(0, "Number of Lora networks to keep cached in memory", gr.Number, {"precision": 0}),
+    "lora_not_found_warning_console": shared.OptionInfo(False, "Lora not found warning in console"),
+    "lora_not_found_gradio_warning": shared.OptionInfo(False, "Lora not found warning popup in webui"),
 }))
 
 

extensions-builtin/Lora/ui_edit_user_metadata.py

@@ -21,10 +21,12 @@ re_comma = re.compile(r" *, *")
 def build_tags(metadata):
     tags = {}
 
-    for _, tags_dict in metadata.get("ss_tag_frequency", {}).items():
-        for tag, tag_count in tags_dict.items():
-            tag = tag.strip()
-            tags[tag] = tags.get(tag, 0) + int(tag_count)
+    ss_tag_frequency = metadata.get("ss_tag_frequency", {})
+    if ss_tag_frequency is not None and hasattr(ss_tag_frequency, 'items'):
+        for _, tags_dict in ss_tag_frequency.items():
+            for tag, tag_count in tags_dict.items():
+                tag = tag.strip()
+                tags[tag] = tags.get(tag, 0) + int(tag_count)
 
     if tags and is_non_comma_tagset(tags):
         new_tags = {}
@@ -54,12 +56,13 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
         self.slider_preferred_weight = None
         self.edit_notes = None
 
-    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, notes):
+    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, negative_text, notes):
         user_metadata = self.get_user_metadata(name)
         user_metadata["description"] = desc
         user_metadata["sd version"] = sd_version
         user_metadata["activation text"] = activation_text
         user_metadata["preferred weight"] = preferred_weight
+        user_metadata["negative text"] = negative_text
         user_metadata["notes"] = notes
 
         self.write_user_metadata(name, user_metadata)
@@ -127,6 +130,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
             gr.HighlightedText.update(value=gradio_tags, visible=True if tags else False),
             user_metadata.get('activation text', ''),
             float(user_metadata.get('preferred weight', 0.0)),
+            user_metadata.get('negative text', ''),
             gr.update(visible=True if tags else False),
             gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
         ]
@@ -147,6 +151,8 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
 
             v = random.random() * max_count
             if count > v:
+                for x in "({[]})":
+                    tag = tag.replace(x, '\\' + x)
                 res.append(tag)
 
         return ", ".join(sorted(res))
@@ -162,7 +168,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
         self.taginfo = gr.HighlightedText(label="Training dataset tags")
         self.edit_activation_text = gr.Text(label='Activation text', info="Will be added to prompt along with Lora")
         self.slider_preferred_weight = gr.Slider(label='Preferred weight', info="Set to 0 to disable", minimum=0.0, maximum=2.0, step=0.01)
-
+        self.edit_negative_text = gr.Text(label='Negative prompt', info="Will be added to negative prompts")
         with gr.Row() as row_random_prompt:
             with gr.Column(scale=8):
                 random_prompt = gr.Textbox(label='Random prompt', lines=4, max_lines=4, interactive=False)
@@ -198,6 +204,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
             self.taginfo,
             self.edit_activation_text,
             self.slider_preferred_weight,
+            self.edit_negative_text,
             row_random_prompt,
             random_prompt,
         ]
@@ -211,7 +218,9 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
             self.select_sd_version,
             self.edit_activation_text,
             self.slider_preferred_weight,
+            self.edit_negative_text,
             self.edit_notes,
         ]
 
+
         self.setup_save_handler(self.button_save, self.save_lora_user_metadata, edited_components)

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -24,13 +24,16 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
 
         alias = lora_on_disk.get_alias()
 
+        search_terms = [self.search_terms_from_path(lora_on_disk.filename)]
+        if lora_on_disk.hash:
+            search_terms.append(lora_on_disk.hash)
         item = {
             "name": name,
             "filename": lora_on_disk.filename,
             "shorthash": lora_on_disk.shorthash,
-            "preview": self.find_preview(path),
+            "preview": self.find_preview(path) or self.find_embedded_preview(path, name, lora_on_disk.metadata),
             "description": self.find_description(path),
-            "search_term": self.search_terms_from_path(lora_on_disk.filename) + " " + (lora_on_disk.hash or ""),
+            "search_terms": search_terms,
             "local_preview": f"{path}.{shared.opts.samples_format}",
             "metadata": lora_on_disk.metadata,
             "sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
@@ -45,6 +48,11 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         if activation_text:
             item["prompt"] += " + " + quote_js(" " + activation_text)
 
+        negative_prompt = item["user_metadata"].get("negative text")
+        item["negative_prompt"] = quote_js("")
+        if negative_prompt:
+            item["negative_prompt"] = quote_js('(' + negative_prompt + ':1)')
+
         sd_version = item["user_metadata"].get("sd version")
         if sd_version in network.SdVersion.__members__:
             item["sd_version"] = sd_version
@@ -52,7 +60,7 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         else:
             sd_version = lora_on_disk.sd_version
 
-        if shared.opts.lora_show_all or not enable_filter:
+        if shared.opts.lora_show_all or not enable_filter or not shared.sd_model:
             pass
         elif sd_version == network.SdVersion.Unknown:
             model_version = network.SdVersion.SDXL if shared.sd_model.is_sdxl else network.SdVersion.SD2 if shared.sd_model.is_sd2 else network.SdVersion.SD1

extensions-builtin/ScuNET/scripts/scunet_model.py

@@ -1,16 +1,9 @@
 import sys
 
 import PIL.Image
-import numpy as np
-import torch
-from tqdm import tqdm
 
 import modules.upscaler
-from modules import devices, modelloader, script_callbacks, errors
-from scunet_model_arch import SCUNet
-
-from modules.modelloader import load_file_from_url
-from modules.shared import opts
+from modules import devices, errors, modelloader, script_callbacks, shared, upscaler_utils
 
 
 class UpscalerScuNET(modules.upscaler.Upscaler):
@@ -42,100 +35,37 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
             scalers.append(scaler_data2)
         self.scalers = scalers
 
-    @staticmethod
-    @torch.no_grad()
-    def tiled_inference(img, model):
-        # test the image tile by tile
-        h, w = img.shape[2:]
-        tile = opts.SCUNET_tile
-        tile_overlap = opts.SCUNET_tile_overlap
-        if tile == 0:
-            return model(img)
-
-        device = devices.get_device_for('scunet')
-        assert tile % 8 == 0, "tile size should be a multiple of window_size"
-        sf = 1
-
-        stride = tile - tile_overlap
-        h_idx_list = list(range(0, h - tile, stride)) + [h - tile]
-        w_idx_list = list(range(0, w - tile, stride)) + [w - tile]
-        E = torch.zeros(1, 3, h * sf, w * sf, dtype=img.dtype, device=device)
-        W = torch.zeros_like(E, dtype=devices.dtype, device=device)
-
-        with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="ScuNET tiles") as pbar:
-            for h_idx in h_idx_list:
-
-                for w_idx in w_idx_list:
-
-                    in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
-
-                    out_patch = model(in_patch)
-                    out_patch_mask = torch.ones_like(out_patch)
-
-                    E[
-                        ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                    ].add_(out_patch)
-                    W[
-                        ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                    ].add_(out_patch_mask)
-                    pbar.update(1)
-        output = E.div_(W)
-
-        return output
-
     def do_upscale(self, img: PIL.Image.Image, selected_file):
-
         devices.torch_gc()
-
         try:
             model = self.load_model(selected_file)
         except Exception as e:
             print(f"ScuNET: Unable to load model from {selected_file}: {e}", file=sys.stderr)
             return img
 
-        device = devices.get_device_for('scunet')
-        tile = opts.SCUNET_tile
-        h, w = img.height, img.width
-        np_img = np.array(img)
-        np_img = np_img[:, :, ::-1]  # RGB to BGR
-        np_img = np_img.transpose((2, 0, 1)) / 255  # HWC to CHW
-        torch_img = torch.from_numpy(np_img).float().unsqueeze(0).to(device)  # type: ignore
-
-        if tile > h or tile > w:
-            _img = torch.zeros(1, 3, max(h, tile), max(w, tile), dtype=torch_img.dtype, device=torch_img.device)
-            _img[:, :, :h, :w] = torch_img # pad image
-            torch_img = _img
-
-        torch_output = self.tiled_inference(torch_img, model).squeeze(0)
-        torch_output = torch_output[:, :h * 1, :w * 1] # remove padding, if any
-        np_output: np.ndarray = torch_output.float().cpu().clamp_(0, 1).numpy()
-        del torch_img, torch_output
+        img = upscaler_utils.upscale_2(
+            img,
+            model,
+            tile_size=shared.opts.SCUNET_tile,
+            tile_overlap=shared.opts.SCUNET_tile_overlap,
+            scale=1,  # ScuNET is a denoising model, not an upscaler
+            desc='ScuNET',
+        )
         devices.torch_gc()
-
-        output = np_output.transpose((1, 2, 0))  # CHW to HWC
-        output = output[:, :, ::-1]  # BGR to RGB
-        return PIL.Image.fromarray((output * 255).astype(np.uint8))
+        return img
 
     def load_model(self, path: str):
         device = devices.get_device_for('scunet')
         if path.startswith("http"):
             # TODO: this doesn't use `path` at all?
-            filename = load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name=f"{self.name}.pth")
+            filename = modelloader.load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name=f"{self.name}.pth")
         else:
             filename = path
-        model = SCUNet(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
-        model.load_state_dict(torch.load(filename), strict=True)
-        model.eval()
-        for _, v in model.named_parameters():
-            v.requires_grad = False
-        model = model.to(device)
-
-        return model
+        return modelloader.load_spandrel_model(filename, device=device, expected_architecture='SCUNet')
 
 
 def on_ui_settings():
     import gradio as gr
-    from modules import shared
 
     shared.opts.add_option("SCUNET_tile", shared.OptionInfo(256, "Tile size for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")).info("0 = no tiling"))
     shared.opts.add_option("SCUNET_tile_overlap", shared.OptionInfo(8, "Tile overlap for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, section=('upscaling', "Upscaling")).info("Low values = visible seam"))

extensions-builtin/ScuNET/scunet_model_arch.py

@@ -1,268 +0,0 @@
-# -*- coding: utf-8 -*-
-import numpy as np
-import torch
-import torch.nn as nn
-from einops import rearrange
-from einops.layers.torch import Rearrange
-from timm.models.layers import trunc_normal_, DropPath
-
-
-class WMSA(nn.Module):
-    """ Self-attention module in Swin Transformer
-    """
-
-    def __init__(self, input_dim, output_dim, head_dim, window_size, type):
-        super(WMSA, self).__init__()
-        self.input_dim = input_dim
-        self.output_dim = output_dim
-        self.head_dim = head_dim
-        self.scale = self.head_dim ** -0.5
-        self.n_heads = input_dim // head_dim
-        self.window_size = window_size
-        self.type = type
-        self.embedding_layer = nn.Linear(self.input_dim, 3 * self.input_dim, bias=True)
-
-        self.relative_position_params = nn.Parameter(
-            torch.zeros((2 * window_size - 1) * (2 * window_size - 1), self.n_heads))
-
-        self.linear = nn.Linear(self.input_dim, self.output_dim)
-
-        trunc_normal_(self.relative_position_params, std=.02)
-        self.relative_position_params = torch.nn.Parameter(
-            self.relative_position_params.view(2 * window_size - 1, 2 * window_size - 1, self.n_heads).transpose(1,
-                                                                                                                 2).transpose(
-                0, 1))
-
-    def generate_mask(self, h, w, p, shift):
-        """ generating the mask of SW-MSA
-        Args:
-            shift: shift parameters in CyclicShift.
-        Returns:
-            attn_mask: should be (1 1 w p p),
-        """
-        # supporting square.
-        attn_mask = torch.zeros(h, w, p, p, p, p, dtype=torch.bool, device=self.relative_position_params.device)
-        if self.type == 'W':
-            return attn_mask
-
-        s = p - shift
-        attn_mask[-1, :, :s, :, s:, :] = True
-        attn_mask[-1, :, s:, :, :s, :] = True
-        attn_mask[:, -1, :, :s, :, s:] = True
-        attn_mask[:, -1, :, s:, :, :s] = True
-        attn_mask = rearrange(attn_mask, 'w1 w2 p1 p2 p3 p4 -> 1 1 (w1 w2) (p1 p2) (p3 p4)')
-        return attn_mask
-
-    def forward(self, x):
-        """ Forward pass of Window Multi-head Self-attention module.
-        Args:
-            x: input tensor with shape of [b h w c];
-            attn_mask: attention mask, fill -inf where the value is True;
-        Returns:
-            output: tensor shape [b h w c]
-        """
-        if self.type != 'W':
-            x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2))
-
-        x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size)
-        h_windows = x.size(1)
-        w_windows = x.size(2)
-        # square validation
-        # assert h_windows == w_windows
-
-        x = rearrange(x, 'b w1 w2 p1 p2 c -> b (w1 w2) (p1 p2) c', p1=self.window_size, p2=self.window_size)
-        qkv = self.embedding_layer(x)
-        q, k, v = rearrange(qkv, 'b nw np (threeh c) -> threeh b nw np c', c=self.head_dim).chunk(3, dim=0)
-        sim = torch.einsum('hbwpc,hbwqc->hbwpq', q, k) * self.scale
-        # Adding learnable relative embedding
-        sim = sim + rearrange(self.relative_embedding(), 'h p q -> h 1 1 p q')
-        # Using Attn Mask to distinguish different subwindows.
-        if self.type != 'W':
-            attn_mask = self.generate_mask(h_windows, w_windows, self.window_size, shift=self.window_size // 2)
-            sim = sim.masked_fill_(attn_mask, float("-inf"))
-
-        probs = nn.functional.softmax(sim, dim=-1)
-        output = torch.einsum('hbwij,hbwjc->hbwic', probs, v)
-        output = rearrange(output, 'h b w p c -> b w p (h c)')
-        output = self.linear(output)
-        output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size)
-
-        if self.type != 'W':
-            output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), dims=(1, 2))
-
-        return output
-
-    def relative_embedding(self):
-        cord = torch.tensor(np.array([[i, j] for i in range(self.window_size) for j in range(self.window_size)]))
-        relation = cord[:, None, :] - cord[None, :, :] + self.window_size - 1
-        # negative is allowed
-        return self.relative_position_params[:, relation[:, :, 0].long(), relation[:, :, 1].long()]
-
-
-class Block(nn.Module):
-    def __init__(self, input_dim, output_dim, head_dim, window_size, drop_path, type='W', input_resolution=None):
-        """ SwinTransformer Block
-        """
-        super(Block, self).__init__()
-        self.input_dim = input_dim
-        self.output_dim = output_dim
-        assert type in ['W', 'SW']
-        self.type = type
-        if input_resolution <= window_size:
-            self.type = 'W'
-
-        self.ln1 = nn.LayerNorm(input_dim)
-        self.msa = WMSA(input_dim, input_dim, head_dim, window_size, self.type)
-        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
-        self.ln2 = nn.LayerNorm(input_dim)
-        self.mlp = nn.Sequential(
-            nn.Linear(input_dim, 4 * input_dim),
-            nn.GELU(),
-            nn.Linear(4 * input_dim, output_dim),
-        )
-
-    def forward(self, x):
-        x = x + self.drop_path(self.msa(self.ln1(x)))
-        x = x + self.drop_path(self.mlp(self.ln2(x)))
-        return x
-
-
-class ConvTransBlock(nn.Module):
-    def __init__(self, conv_dim, trans_dim, head_dim, window_size, drop_path, type='W', input_resolution=None):
-        """ SwinTransformer and Conv Block
-        """
-        super(ConvTransBlock, self).__init__()
-        self.conv_dim = conv_dim
-        self.trans_dim = trans_dim
-        self.head_dim = head_dim
-        self.window_size = window_size
-        self.drop_path = drop_path
-        self.type = type
-        self.input_resolution = input_resolution
-
-        assert self.type in ['W', 'SW']
-        if self.input_resolution <= self.window_size:
-            self.type = 'W'
-
-        self.trans_block = Block(self.trans_dim, self.trans_dim, self.head_dim, self.window_size, self.drop_path,
-                                 self.type, self.input_resolution)
-        self.conv1_1 = nn.Conv2d(self.conv_dim + self.trans_dim, self.conv_dim + self.trans_dim, 1, 1, 0, bias=True)
-        self.conv1_2 = nn.Conv2d(self.conv_dim + self.trans_dim, self.conv_dim + self.trans_dim, 1, 1, 0, bias=True)
-
-        self.conv_block = nn.Sequential(
-            nn.Conv2d(self.conv_dim, self.conv_dim, 3, 1, 1, bias=False),
-            nn.ReLU(True),
-            nn.Conv2d(self.conv_dim, self.conv_dim, 3, 1, 1, bias=False)
-        )
-
-    def forward(self, x):
-        conv_x, trans_x = torch.split(self.conv1_1(x), (self.conv_dim, self.trans_dim), dim=1)
-        conv_x = self.conv_block(conv_x) + conv_x
-        trans_x = Rearrange('b c h w -> b h w c')(trans_x)
-        trans_x = self.trans_block(trans_x)
-        trans_x = Rearrange('b h w c -> b c h w')(trans_x)
-        res = self.conv1_2(torch.cat((conv_x, trans_x), dim=1))
-        x = x + res
-
-        return x
-
-
-class SCUNet(nn.Module):
-    # def __init__(self, in_nc=3, config=[2, 2, 2, 2, 2, 2, 2], dim=64, drop_path_rate=0.0, input_resolution=256):
-    def __init__(self, in_nc=3, config=None, dim=64, drop_path_rate=0.0, input_resolution=256):
-        super(SCUNet, self).__init__()
-        if config is None:
-            config = [2, 2, 2, 2, 2, 2, 2]
-        self.config = config
-        self.dim = dim
-        self.head_dim = 32
-        self.window_size = 8
-
-        # drop path rate for each layer
-        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(config))]
-
-        self.m_head = [nn.Conv2d(in_nc, dim, 3, 1, 1, bias=False)]
-
-        begin = 0
-        self.m_down1 = [ConvTransBlock(dim // 2, dim // 2, self.head_dim, self.window_size, dpr[i + begin],
-                                       'W' if not i % 2 else 'SW', input_resolution)
-                        for i in range(config[0])] + \
-                       [nn.Conv2d(dim, 2 * dim, 2, 2, 0, bias=False)]
-
-        begin += config[0]
-        self.m_down2 = [ConvTransBlock(dim, dim, self.head_dim, self.window_size, dpr[i + begin],
-                                       'W' if not i % 2 else 'SW', input_resolution // 2)
-                        for i in range(config[1])] + \
-                       [nn.Conv2d(2 * dim, 4 * dim, 2, 2, 0, bias=False)]
-
-        begin += config[1]
-        self.m_down3 = [ConvTransBlock(2 * dim, 2 * dim, self.head_dim, self.window_size, dpr[i + begin],
-                                       'W' if not i % 2 else 'SW', input_resolution // 4)
-                        for i in range(config[2])] + \
-                       [nn.Conv2d(4 * dim, 8 * dim, 2, 2, 0, bias=False)]
-
-        begin += config[2]
-        self.m_body = [ConvTransBlock(4 * dim, 4 * dim, self.head_dim, self.window_size, dpr[i + begin],
-                                      'W' if not i % 2 else 'SW', input_resolution // 8)
-                       for i in range(config[3])]
-
-        begin += config[3]
-        self.m_up3 = [nn.ConvTranspose2d(8 * dim, 4 * dim, 2, 2, 0, bias=False), ] + \
-                     [ConvTransBlock(2 * dim, 2 * dim, self.head_dim, self.window_size, dpr[i + begin],
-                                     'W' if not i % 2 else 'SW', input_resolution // 4)
-                      for i in range(config[4])]
-
-        begin += config[4]
-        self.m_up2 = [nn.ConvTranspose2d(4 * dim, 2 * dim, 2, 2, 0, bias=False), ] + \
-                     [ConvTransBlock(dim, dim, self.head_dim, self.window_size, dpr[i + begin],
-                                     'W' if not i % 2 else 'SW', input_resolution // 2)
-                      for i in range(config[5])]
-
-        begin += config[5]
-        self.m_up1 = [nn.ConvTranspose2d(2 * dim, dim, 2, 2, 0, bias=False), ] + \
-                     [ConvTransBlock(dim // 2, dim // 2, self.head_dim, self.window_size, dpr[i + begin],
-                                     'W' if not i % 2 else 'SW', input_resolution)
-                      for i in range(config[6])]
-
-        self.m_tail = [nn.Conv2d(dim, in_nc, 3, 1, 1, bias=False)]
-
-        self.m_head = nn.Sequential(*self.m_head)
-        self.m_down1 = nn.Sequential(*self.m_down1)
-        self.m_down2 = nn.Sequential(*self.m_down2)
-        self.m_down3 = nn.Sequential(*self.m_down3)
-        self.m_body = nn.Sequential(*self.m_body)
-        self.m_up3 = nn.Sequential(*self.m_up3)
-        self.m_up2 = nn.Sequential(*self.m_up2)
-        self.m_up1 = nn.Sequential(*self.m_up1)
-        self.m_tail = nn.Sequential(*self.m_tail)
-        # self.apply(self._init_weights)
-
-    def forward(self, x0):
-
-        h, w = x0.size()[-2:]
-        paddingBottom = int(np.ceil(h / 64) * 64 - h)
-        paddingRight = int(np.ceil(w / 64) * 64 - w)
-        x0 = nn.ReplicationPad2d((0, paddingRight, 0, paddingBottom))(x0)
-
-        x1 = self.m_head(x0)
-        x2 = self.m_down1(x1)
-        x3 = self.m_down2(x2)
-        x4 = self.m_down3(x3)
-        x = self.m_body(x4)
-        x = self.m_up3(x + x4)
-        x = self.m_up2(x + x3)
-        x = self.m_up1(x + x2)
-        x = self.m_tail(x + x1)
-
-        x = x[..., :h, :w]
-
-        return x
-
-    def _init_weights(self, m):
-        if isinstance(m, nn.Linear):
-            trunc_normal_(m.weight, std=.02)
-            if m.bias is not None:
-                nn.init.constant_(m.bias, 0)
-        elif isinstance(m, nn.LayerNorm):
-            nn.init.constant_(m.bias, 0)
-            nn.init.constant_(m.weight, 1.0)

extensions-builtin/SwinIR/scripts/swinir_model.py

@@ -1,20 +1,15 @@
+import logging
 import sys
-import platform
 
-import numpy as np
 import torch
 from PIL import Image
-from tqdm import tqdm
 
-from modules import modelloader, devices, script_callbacks, shared
-from modules.shared import opts, state
-from swinir_model_arch import SwinIR
-from swinir_model_arch_v2 import Swin2SR
+from modules import devices, modelloader, script_callbacks, shared, upscaler_utils
 from modules.upscaler import Upscaler, UpscalerData
 
 SWINIR_MODEL_URL = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth"
 
-device_swinir = devices.get_device_for('swinir')
+logger = logging.getLogger(__name__)
 
 
 class UpscalerSwinIR(Upscaler):
@@ -37,26 +32,28 @@ class UpscalerSwinIR(Upscaler):
             scalers.append(model_data)
         self.scalers = scalers
 
-    def do_upscale(self, img, model_file):
-        use_compile = hasattr(opts, 'SWIN_torch_compile') and opts.SWIN_torch_compile \
-            and int(torch.__version__.split('.')[0]) >= 2 and platform.system() != "Windows"
-        current_config = (model_file, opts.SWIN_tile)
+    def do_upscale(self, img: Image.Image, model_file: str) -> Image.Image:
+        current_config = (model_file, shared.opts.SWIN_tile)
 
-        if use_compile and self._cached_model_config == current_config:
+        if self._cached_model_config == current_config:
             model = self._cached_model
         else:
-            self._cached_model = None
             try:
                 model = self.load_model(model_file)
             except Exception as e:
                 print(f"Failed loading SwinIR model {model_file}: {e}", file=sys.stderr)
                 return img
-            model = model.to(device_swinir, dtype=devices.dtype)
-            if use_compile:
-                model = torch.compile(model)
-                self._cached_model = model
-                self._cached_model_config = current_config
-        img = upscale(img, model)
+            self._cached_model = model
+            self._cached_model_config = current_config
+
+        img = upscaler_utils.upscale_2(
+            img,
+            model,
+            tile_size=shared.opts.SWIN_tile,
+            tile_overlap=shared.opts.SWIN_tile_overlap,
+            scale=model.scale,
+            desc="SwinIR",
+        )
         devices.torch_gc()
         return img
 
@@ -69,115 +66,22 @@ class UpscalerSwinIR(Upscaler):
             )
         else:
             filename = path
-        if filename.endswith(".v2.pth"):
-            model = Swin2SR(
-                upscale=scale,
-                in_chans=3,
-                img_size=64,
-                window_size=8,
-                img_range=1.0,
-                depths=[6, 6, 6, 6, 6, 6],
-                embed_dim=180,
-                num_heads=[6, 6, 6, 6, 6, 6],
-                mlp_ratio=2,
-                upsampler="nearest+conv",
-                resi_connection="1conv",
-            )
-            params = None
-        else:
-            model = SwinIR(
-                upscale=scale,
-                in_chans=3,
-                img_size=64,
-                window_size=8,
-                img_range=1.0,
-                depths=[6, 6, 6, 6, 6, 6, 6, 6, 6],
-                embed_dim=240,
-                num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8],
-                mlp_ratio=2,
-                upsampler="nearest+conv",
-                resi_connection="3conv",
-            )
-            params = "params_ema"
 
-        pretrained_model = torch.load(filename)
-        if params is not None:
-            model.load_state_dict(pretrained_model[params], strict=True)
-        else:
-            model.load_state_dict(pretrained_model, strict=True)
-        return model
+        model_descriptor = modelloader.load_spandrel_model(
+            filename,
+            device=self._get_device(),
+            prefer_half=(devices.dtype == torch.float16),
+            expected_architecture="SwinIR",
+        )
+        if getattr(shared.opts, 'SWIN_torch_compile', False):
+            try:
+                model_descriptor.model.compile()
+            except Exception:
+                logger.warning("Failed to compile SwinIR model, fallback to JIT", exc_info=True)
+        return model_descriptor
 
-
-def upscale(
-        img,
-        model,
-        tile=None,
-        tile_overlap=None,
-        window_size=8,
-        scale=4,
-):
-    tile = tile or opts.SWIN_tile
-    tile_overlap = tile_overlap or opts.SWIN_tile_overlap
-
-
-    img = np.array(img)
-    img = img[:, :, ::-1]
-    img = np.moveaxis(img, 2, 0) / 255
-    img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(device_swinir, dtype=devices.dtype)
-    with torch.no_grad(), devices.autocast():
-        _, _, h_old, w_old = img.size()
-        h_pad = (h_old // window_size + 1) * window_size - h_old
-        w_pad = (w_old // window_size + 1) * window_size - w_old
-        img = torch.cat([img, torch.flip(img, [2])], 2)[:, :, : h_old + h_pad, :]
-        img = torch.cat([img, torch.flip(img, [3])], 3)[:, :, :, : w_old + w_pad]
-        output = inference(img, model, tile, tile_overlap, window_size, scale)
-        output = output[..., : h_old * scale, : w_old * scale]
-        output = output.data.squeeze().float().cpu().clamp_(0, 1).numpy()
-        if output.ndim == 3:
-            output = np.transpose(
-                output[[2, 1, 0], :, :], (1, 2, 0)
-            )  # CHW-RGB to HCW-BGR
-        output = (output * 255.0).round().astype(np.uint8)  # float32 to uint8
-        return Image.fromarray(output, "RGB")
-
-
-def inference(img, model, tile, tile_overlap, window_size, scale):
-    # test the image tile by tile
-    b, c, h, w = img.size()
-    tile = min(tile, h, w)
-    assert tile % window_size == 0, "tile size should be a multiple of window_size"
-    sf = scale
-
-    stride = tile - tile_overlap
-    h_idx_list = list(range(0, h - tile, stride)) + [h - tile]
-    w_idx_list = list(range(0, w - tile, stride)) + [w - tile]
-    E = torch.zeros(b, c, h * sf, w * sf, dtype=devices.dtype, device=device_swinir).type_as(img)
-    W = torch.zeros_like(E, dtype=devices.dtype, device=device_swinir)
-
-    with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="SwinIR tiles") as pbar:
-        for h_idx in h_idx_list:
-            if state.interrupted or state.skipped:
-                break
-
-            for w_idx in w_idx_list:
-                if state.interrupted or state.skipped:
-                    break
-
-                in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
-                out_patch = model(in_patch)
-                out_patch_mask = torch.ones_like(out_patch)
-
-                E[
-                ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                ].add_(out_patch)
-                W[
-                ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                ].add_(out_patch_mask)
-                pbar.update(1)
-    output = E.div_(W)
-
-    return output
+    def _get_device(self):
+        return devices.get_device_for('swinir')
 
 
 def on_ui_settings():
@@ -185,8 +89,7 @@ def on_ui_settings():
 
     shared.opts.add_option("SWIN_tile", shared.OptionInfo(192, "Tile size for all SwinIR.", gr.Slider, {"minimum": 16, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")))
     shared.opts.add_option("SWIN_tile_overlap", shared.OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}, section=('upscaling', "Upscaling")))
-    if int(torch.__version__.split('.')[0]) >= 2 and platform.system() != "Windows":    # torch.compile() require pytorch 2.0 or above, and not on Windows
-        shared.opts.add_option("SWIN_torch_compile", shared.OptionInfo(False, "Use torch.compile to accelerate SwinIR.", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")).info("Takes longer on first run"))
+    shared.opts.add_option("SWIN_torch_compile", shared.OptionInfo(False, "Use torch.compile to accelerate SwinIR.", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")).info("Takes longer on first run"))
 
 
 script_callbacks.on_ui_settings(on_ui_settings)

extensions-builtin/SwinIR/swinir_model_arch.py

@@ -1,867 +0,0 @@
-# -----------------------------------------------------------------------------------
-# SwinIR: Image Restoration Using Swin Transformer, https://arxiv.org/abs/2108.10257
-# Originally Written by Ze Liu, Modified by Jingyun Liang.
-# -----------------------------------------------------------------------------------
-
-import math
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import torch.utils.checkpoint as checkpoint
-from timm.models.layers import DropPath, to_2tuple, trunc_normal_
-
-
-class Mlp(nn.Module):
-    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
-        super().__init__()
-        out_features = out_features or in_features
-        hidden_features = hidden_features or in_features
-        self.fc1 = nn.Linear(in_features, hidden_features)
-        self.act = act_layer()
-        self.fc2 = nn.Linear(hidden_features, out_features)
-        self.drop = nn.Dropout(drop)
-
-    def forward(self, x):
-        x = self.fc1(x)
-        x = self.act(x)
-        x = self.drop(x)
-        x = self.fc2(x)
-        x = self.drop(x)
-        return x
-
-
-def window_partition(x, window_size):
-    """
-    Args:
-        x: (B, H, W, C)
-        window_size (int): window size
-
-    Returns:
-        windows: (num_windows*B, window_size, window_size, C)
-    """
-    B, H, W, C = x.shape
-    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
-    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
-    return windows
-
-
-def window_reverse(windows, window_size, H, W):
-    """
-    Args:
-        windows: (num_windows*B, window_size, window_size, C)
-        window_size (int): Window size
-        H (int): Height of image
-        W (int): Width of image
-
-    Returns:
-        x: (B, H, W, C)
-    """
-    B = int(windows.shape[0] / (H * W / window_size / window_size))
-    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
-    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
-    return x
-
-
-class WindowAttention(nn.Module):
-    r""" Window based multi-head self attention (W-MSA) module with relative position bias.
-    It supports both of shifted and non-shifted window.
-
-    Args:
-        dim (int): Number of input channels.
-        window_size (tuple[int]): The height and width of the window.
-        num_heads (int): Number of attention heads.
-        qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
-        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
-        attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
-        proj_drop (float, optional): Dropout ratio of output. Default: 0.0
-    """
-
-    def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):
-
-        super().__init__()
-        self.dim = dim
-        self.window_size = window_size  # Wh, Ww
-        self.num_heads = num_heads
-        head_dim = dim // num_heads
-        self.scale = qk_scale or head_dim ** -0.5
-
-        # define a parameter table of relative position bias
-        self.relative_position_bias_table = nn.Parameter(
-            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))  # 2*Wh-1 * 2*Ww-1, nH
-
-        # get pair-wise relative position index for each token inside the window
-        coords_h = torch.arange(self.window_size[0])
-        coords_w = torch.arange(self.window_size[1])
-        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
-        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
-        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
-        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
-        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
-        relative_coords[:, :, 1] += self.window_size[1] - 1
-        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
-        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
-        self.register_buffer("relative_position_index", relative_position_index)
-
-        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
-        self.attn_drop = nn.Dropout(attn_drop)
-        self.proj = nn.Linear(dim, dim)
-
-        self.proj_drop = nn.Dropout(proj_drop)
-
-        trunc_normal_(self.relative_position_bias_table, std=.02)
-        self.softmax = nn.Softmax(dim=-1)
-
-    def forward(self, x, mask=None):
-        """
-        Args:
-            x: input features with shape of (num_windows*B, N, C)
-            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
-        """
-        B_, N, C = x.shape
-        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
-        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)
-
-        q = q * self.scale
-        attn = (q @ k.transpose(-2, -1))
-
-        relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
-            self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
-        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
-        attn = attn + relative_position_bias.unsqueeze(0)
-
-        if mask is not None:
-            nW = mask.shape[0]
-            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
-            attn = attn.view(-1, self.num_heads, N, N)
-            attn = self.softmax(attn)
-        else:
-            attn = self.softmax(attn)
-
-        attn = self.attn_drop(attn)
-
-        x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
-        x = self.proj(x)
-        x = self.proj_drop(x)
-        return x
-
-    def extra_repr(self) -> str:
-        return f'dim={self.dim}, window_size={self.window_size}, num_heads={self.num_heads}'
-
-    def flops(self, N):
-        # calculate flops for 1 window with token length of N
-        flops = 0
-        # qkv = self.qkv(x)
-        flops += N * self.dim * 3 * self.dim
-        # attn = (q @ k.transpose(-2, -1))
-        flops += self.num_heads * N * (self.dim // self.num_heads) * N
-        #  x = (attn @ v)
-        flops += self.num_heads * N * N * (self.dim // self.num_heads)
-        # x = self.proj(x)
-        flops += N * self.dim * self.dim
-        return flops
-
-
-class SwinTransformerBlock(nn.Module):
-    r""" Swin Transformer Block.
-
-    Args:
-        dim (int): Number of input channels.
-        input_resolution (tuple[int]): Input resolution.
-        num_heads (int): Number of attention heads.
-        window_size (int): Window size.
-        shift_size (int): Shift size for SW-MSA.
-        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
-        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
-        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
-        drop (float, optional): Dropout rate. Default: 0.0
-        attn_drop (float, optional): Attention dropout rate. Default: 0.0
-        drop_path (float, optional): Stochastic depth rate. Default: 0.0
-        act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
-        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
-    """
-
-    def __init__(self, dim, input_resolution, num_heads, window_size=7, shift_size=0,
-                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
-                 act_layer=nn.GELU, norm_layer=nn.LayerNorm):
-        super().__init__()
-        self.dim = dim
-        self.input_resolution = input_resolution
-        self.num_heads = num_heads
-        self.window_size = window_size
-        self.shift_size = shift_size
-        self.mlp_ratio = mlp_ratio
-        if min(self.input_resolution) <= self.window_size:
-            # if window size is larger than input resolution, we don't partition windows
-            self.shift_size = 0
-            self.window_size = min(self.input_resolution)
-        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"
-
-        self.norm1 = norm_layer(dim)
-        self.attn = WindowAttention(
-            dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,
-            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
-
-        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
-        self.norm2 = norm_layer(dim)
-        mlp_hidden_dim = int(dim * mlp_ratio)
-        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
-
-        if self.shift_size > 0:
-            attn_mask = self.calculate_mask(self.input_resolution)
-        else:
-            attn_mask = None
-
-        self.register_buffer("attn_mask", attn_mask)
-
-    def calculate_mask(self, x_size):
-        # calculate attention mask for SW-MSA
-        H, W = x_size
-        img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1
-        h_slices = (slice(0, -self.window_size),
-                    slice(-self.window_size, -self.shift_size),
-                    slice(-self.shift_size, None))
-        w_slices = (slice(0, -self.window_size),
-                    slice(-self.window_size, -self.shift_size),
-                    slice(-self.shift_size, None))
-        cnt = 0
-        for h in h_slices:
-            for w in w_slices:
-                img_mask[:, h, w, :] = cnt
-                cnt += 1
-
-        mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
-        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
-        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
-        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
-
-        return attn_mask
-
-    def forward(self, x, x_size):
-        H, W = x_size
-        B, L, C = x.shape
-        # assert L == H * W, "input feature has wrong size"
-
-        shortcut = x
-        x = self.norm1(x)
-        x = x.view(B, H, W, C)
-
-        # cyclic shift
-        if self.shift_size > 0:
-            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
-        else:
-            shifted_x = x
-
-        # partition windows
-        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
-        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C
-
-        # W-MSA/SW-MSA (to be compatible for testing on images whose shapes are the multiple of window size
-        if self.input_resolution == x_size:
-            attn_windows = self.attn(x_windows, mask=self.attn_mask)  # nW*B, window_size*window_size, C
-        else:
-            attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device))
-
-        # merge windows
-        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
-        shifted_x = window_reverse(attn_windows, self.window_size, H, W)  # B H' W' C
-
-        # reverse cyclic shift
-        if self.shift_size > 0:
-            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
-        else:
-            x = shifted_x
-        x = x.view(B, H * W, C)
-
-        # FFN
-        x = shortcut + self.drop_path(x)
-        x = x + self.drop_path(self.mlp(self.norm2(x)))
-
-        return x
-
-    def extra_repr(self) -> str:
-        return f"dim={self.dim}, input_resolution={self.input_resolution}, num_heads={self.num_heads}, " \
-               f"window_size={self.window_size}, shift_size={self.shift_size}, mlp_ratio={self.mlp_ratio}"
-
-    def flops(self):
-        flops = 0
-        H, W = self.input_resolution
-        # norm1
-        flops += self.dim * H * W
-        # W-MSA/SW-MSA
-        nW = H * W / self.window_size / self.window_size
-        flops += nW * self.attn.flops(self.window_size * self.window_size)
-        # mlp
-        flops += 2 * H * W * self.dim * self.dim * self.mlp_ratio
-        # norm2
-        flops += self.dim * H * W
-        return flops
-
-
-class PatchMerging(nn.Module):
-    r""" Patch Merging Layer.
-
-    Args:
-        input_resolution (tuple[int]): Resolution of input feature.
-        dim (int): Number of input channels.
-        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
-    """
-
-    def __init__(self, input_resolution, dim, norm_layer=nn.LayerNorm):
-        super().__init__()
-        self.input_resolution = input_resolution
-        self.dim = dim
-        self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
-        self.norm = norm_layer(4 * dim)
-
-    def forward(self, x):
-        """
-        x: B, H*W, C
-        """
-        H, W = self.input_resolution
-        B, L, C = x.shape
-        assert L == H * W, "input feature has wrong size"
-        assert H % 2 == 0 and W % 2 == 0, f"x size ({H}*{W}) are not even."
-
-        x = x.view(B, H, W, C)
-
-        x0 = x[:, 0::2, 0::2, :]  # B H/2 W/2 C
-        x1 = x[:, 1::2, 0::2, :]  # B H/2 W/2 C
-        x2 = x[:, 0::2, 1::2, :]  # B H/2 W/2 C
-        x3 = x[:, 1::2, 1::2, :]  # B H/2 W/2 C
-        x = torch.cat([x0, x1, x2, x3], -1)  # B H/2 W/2 4*C
-        x = x.view(B, -1, 4 * C)  # B H/2*W/2 4*C
-
-        x = self.norm(x)
-        x = self.reduction(x)
-
-        return x
-
-    def extra_repr(self) -> str:
-        return f"input_resolution={self.input_resolution}, dim={self.dim}"
-
-    def flops(self):
-        H, W = self.input_resolution
-        flops = H * W * self.dim
-        flops += (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim
-        return flops
-
-
-class BasicLayer(nn.Module):
-    """ A basic Swin Transformer layer for one stage.
-
-    Args:
-        dim (int): Number of input channels.
-        input_resolution (tuple[int]): Input resolution.
-        depth (int): Number of blocks.
-        num_heads (int): Number of attention heads.
-        window_size (int): Local window size.
-        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
-        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
-        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
-        drop (float, optional): Dropout rate. Default: 0.0
-        attn_drop (float, optional): Attention dropout rate. Default: 0.0
-        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
-        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
-        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
-        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
-    """
-
-    def __init__(self, dim, input_resolution, depth, num_heads, window_size,
-                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
-                 drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False):
-
-        super().__init__()
-        self.dim = dim
-        self.input_resolution = input_resolution
-        self.depth = depth
-        self.use_checkpoint = use_checkpoint
-
-        # build blocks
-        self.blocks = nn.ModuleList([
-            SwinTransformerBlock(dim=dim, input_resolution=input_resolution,
-                                 num_heads=num_heads, window_size=window_size,
-                                 shift_size=0 if (i % 2 == 0) else window_size // 2,
-                                 mlp_ratio=mlp_ratio,
-                                 qkv_bias=qkv_bias, qk_scale=qk_scale,
-                                 drop=drop, attn_drop=attn_drop,
-                                 drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
-                                 norm_layer=norm_layer)
-            for i in range(depth)])
-
-        # patch merging layer
-        if downsample is not None:
-            self.downsample = downsample(input_resolution, dim=dim, norm_layer=norm_layer)
-        else:
-            self.downsample = None
-
-    def forward(self, x, x_size):
-        for blk in self.blocks:
-            if self.use_checkpoint:
-                x = checkpoint.checkpoint(blk, x, x_size)
-            else:
-                x = blk(x, x_size)
-        if self.downsample is not None:
-            x = self.downsample(x)
-        return x
-
-    def extra_repr(self) -> str:
-        return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}"
-
-    def flops(self):
-        flops = 0
-        for blk in self.blocks:
-            flops += blk.flops()
-        if self.downsample is not None:
-            flops += self.downsample.flops()
-        return flops
-
-
-class RSTB(nn.Module):
-    """Residual Swin Transformer Block (RSTB).
-
-    Args:
-        dim (int): Number of input channels.
-        input_resolution (tuple[int]): Input resolution.
-        depth (int): Number of blocks.
-        num_heads (int): Number of attention heads.
-        window_size (int): Local window size.
-        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
-        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
-        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
-        drop (float, optional): Dropout rate. Default: 0.0
-        attn_drop (float, optional): Attention dropout rate. Default: 0.0
-        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
-        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
-        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
-        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
-        img_size: Input image size.
-        patch_size: Patch size.
-        resi_connection: The convolutional block before residual connection.
-    """
-
-    def __init__(self, dim, input_resolution, depth, num_heads, window_size,
-                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
-                 drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False,
-                 img_size=224, patch_size=4, resi_connection='1conv'):
-        super(RSTB, self).__init__()
-
-        self.dim = dim
-        self.input_resolution = input_resolution
-
-        self.residual_group = BasicLayer(dim=dim,
-                                         input_resolution=input_resolution,
-                                         depth=depth,
-                                         num_heads=num_heads,
-                                         window_size=window_size,
-                                         mlp_ratio=mlp_ratio,
-                                         qkv_bias=qkv_bias, qk_scale=qk_scale,
-                                         drop=drop, attn_drop=attn_drop,
-                                         drop_path=drop_path,
-                                         norm_layer=norm_layer,
-                                         downsample=downsample,
-                                         use_checkpoint=use_checkpoint)
-
-        if resi_connection == '1conv':
-            self.conv = nn.Conv2d(dim, dim, 3, 1, 1)
-        elif resi_connection == '3conv':
-            # to save parameters and memory
-            self.conv = nn.Sequential(nn.Conv2d(dim, dim // 4, 3, 1, 1), nn.LeakyReLU(negative_slope=0.2, inplace=True),
-                                      nn.Conv2d(dim // 4, dim // 4, 1, 1, 0),
-                                      nn.LeakyReLU(negative_slope=0.2, inplace=True),
-                                      nn.Conv2d(dim // 4, dim, 3, 1, 1))
-
-        self.patch_embed = PatchEmbed(
-            img_size=img_size, patch_size=patch_size, in_chans=0, embed_dim=dim,
-            norm_layer=None)
-
-        self.patch_unembed = PatchUnEmbed(
-            img_size=img_size, patch_size=patch_size, in_chans=0, embed_dim=dim,
-            norm_layer=None)
-
-    def forward(self, x, x_size):
-        return self.patch_embed(self.conv(self.patch_unembed(self.residual_group(x, x_size), x_size))) + x
-
-    def flops(self):
-        flops = 0
-        flops += self.residual_group.flops()
-        H, W = self.input_resolution
-        flops += H * W * self.dim * self.dim * 9
-        flops += self.patch_embed.flops()
-        flops += self.patch_unembed.flops()
-
-        return flops
-
-
-class PatchEmbed(nn.Module):
-    r""" Image to Patch Embedding
-
-    Args:
-        img_size (int): Image size.  Default: 224.
-        patch_size (int): Patch token size. Default: 4.
-        in_chans (int): Number of input image channels. Default: 3.
-        embed_dim (int): Number of linear projection output channels. Default: 96.
-        norm_layer (nn.Module, optional): Normalization layer. Default: None
-    """
-
-    def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
-        super().__init__()
-        img_size = to_2tuple(img_size)
-        patch_size = to_2tuple(patch_size)
-        patches_resolution = [img_size[0] // patch_size[0], img_size[1] // patch_size[1]]
-        self.img_size = img_size
-        self.patch_size = patch_size
-        self.patches_resolution = patches_resolution
-        self.num_patches = patches_resolution[0] * patches_resolution[1]
-
-        self.in_chans = in_chans
-        self.embed_dim = embed_dim
-
-        if norm_layer is not None:
-            self.norm = norm_layer(embed_dim)
-        else:
-            self.norm = None
-
-    def forward(self, x):
-        x = x.flatten(2).transpose(1, 2)  # B Ph*Pw C
-        if self.norm is not None:
-            x = self.norm(x)
-        return x
-
-    def flops(self):
-        flops = 0
-        H, W = self.img_size
-        if self.norm is not None:
-            flops += H * W * self.embed_dim
-        return flops
-
-
-class PatchUnEmbed(nn.Module):
-    r""" Image to Patch Unembedding
-
-    Args:
-        img_size (int): Image size.  Default: 224.
-        patch_size (int): Patch token size. Default: 4.
-        in_chans (int): Number of input image channels. Default: 3.
-        embed_dim (int): Number of linear projection output channels. Default: 96.
-        norm_layer (nn.Module, optional): Normalization layer. Default: None
-    """
-
-    def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
-        super().__init__()
-        img_size = to_2tuple(img_size)
-        patch_size = to_2tuple(patch_size)
-        patches_resolution = [img_size[0] // patch_size[0], img_size[1] // patch_size[1]]
-        self.img_size = img_size
-        self.patch_size = patch_size
-        self.patches_resolution = patches_resolution
-        self.num_patches = patches_resolution[0] * patches_resolution[1]
-
-        self.in_chans = in_chans
-        self.embed_dim = embed_dim
-
-    def forward(self, x, x_size):
-        B, HW, C = x.shape
-        x = x.transpose(1, 2).view(B, self.embed_dim, x_size[0], x_size[1])  # B Ph*Pw C
-        return x
-
-    def flops(self):
-        flops = 0
-        return flops
-
-
-class Upsample(nn.Sequential):
-    """Upsample module.
-
-    Args:
-        scale (int): Scale factor. Supported scales: 2^n and 3.
-        num_feat (int): Channel number of intermediate features.
-    """
-
-    def __init__(self, scale, num_feat):
-        m = []
-        if (scale & (scale - 1)) == 0:  # scale = 2^n
-            for _ in range(int(math.log(scale, 2))):
-                m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1))
-                m.append(nn.PixelShuffle(2))
-        elif scale == 3:
-            m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1))
-            m.append(nn.PixelShuffle(3))
-        else:
-            raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
-        super(Upsample, self).__init__(*m)
-
-
-class UpsampleOneStep(nn.Sequential):
-    """UpsampleOneStep module (the difference with Upsample is that it always only has 1conv + 1pixelshuffle)
-       Used in lightweight SR to save parameters.
-
-    Args:
-        scale (int): Scale factor. Supported scales: 2^n and 3.
-        num_feat (int): Channel number of intermediate features.
-
-    """
-
-    def __init__(self, scale, num_feat, num_out_ch, input_resolution=None):
-        self.num_feat = num_feat
-        self.input_resolution = input_resolution
-        m = []
-        m.append(nn.Conv2d(num_feat, (scale ** 2) * num_out_ch, 3, 1, 1))
-        m.append(nn.PixelShuffle(scale))
-        super(UpsampleOneStep, self).__init__(*m)
-
-    def flops(self):
-        H, W = self.input_resolution
-        flops = H * W * self.num_feat * 3 * 9
-        return flops
-
-
-class SwinIR(nn.Module):
-    r""" SwinIR
-        A PyTorch impl of : `SwinIR: Image Restoration Using Swin Transformer`, based on Swin Transformer.
-
-    Args:
-        img_size (int | tuple(int)): Input image size. Default 64
-        patch_size (int | tuple(int)): Patch size. Default: 1
-        in_chans (int): Number of input image channels. Default: 3
-        embed_dim (int): Patch embedding dimension. Default: 96
-        depths (tuple(int)): Depth of each Swin Transformer layer.
-        num_heads (tuple(int)): Number of attention heads in different layers.
-        window_size (int): Window size. Default: 7
-        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4
-        qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
-        qk_scale (float): Override default qk scale of head_dim ** -0.5 if set. Default: None
-        drop_rate (float): Dropout rate. Default: 0
-        attn_drop_rate (float): Attention dropout rate. Default: 0
-        drop_path_rate (float): Stochastic depth rate. Default: 0.1
-        norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
-        ape (bool): If True, add absolute position embedding to the patch embedding. Default: False
-        patch_norm (bool): If True, add normalization after patch embedding. Default: True
-        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False
-        upscale: Upscale factor. 2/3/4/8 for image SR, 1 for denoising and compress artifact reduction
-        img_range: Image range. 1. or 255.
-        upsampler: The reconstruction reconstruction module. 'pixelshuffle'/'pixelshuffledirect'/'nearest+conv'/None
-        resi_connection: The convolutional block before residual connection. '1conv'/'3conv'
-    """
-
-    def __init__(self, img_size=64, patch_size=1, in_chans=3,
-                 embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6),
-                 window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
-                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
-                 norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
-                 use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv',
-                 **kwargs):
-        super(SwinIR, self).__init__()
-        num_in_ch = in_chans
-        num_out_ch = in_chans
-        num_feat = 64
-        self.img_range = img_range
-        if in_chans == 3:
-            rgb_mean = (0.4488, 0.4371, 0.4040)
-            self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1)
-        else:
-            self.mean = torch.zeros(1, 1, 1, 1)
-        self.upscale = upscale
-        self.upsampler = upsampler
-        self.window_size = window_size
-
-        #####################################################################################################
-        ################################### 1, shallow feature extraction ###################################
-        self.conv_first = nn.Conv2d(num_in_ch, embed_dim, 3, 1, 1)
-
-        #####################################################################################################
-        ################################### 2, deep feature extraction ######################################
-        self.num_layers = len(depths)
-        self.embed_dim = embed_dim
-        self.ape = ape
-        self.patch_norm = patch_norm
-        self.num_features = embed_dim
-        self.mlp_ratio = mlp_ratio
-
-        # split image into non-overlapping patches
-        self.patch_embed = PatchEmbed(
-            img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
-            norm_layer=norm_layer if self.patch_norm else None)
-        num_patches = self.patch_embed.num_patches
-        patches_resolution = self.patch_embed.patches_resolution
-        self.patches_resolution = patches_resolution
-
-        # merge non-overlapping patches into image
-        self.patch_unembed = PatchUnEmbed(
-            img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
-            norm_layer=norm_layer if self.patch_norm else None)
-
-        # absolute position embedding
-        if self.ape:
-            self.absolute_pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim))
-            trunc_normal_(self.absolute_pos_embed, std=.02)
-
-        self.pos_drop = nn.Dropout(p=drop_rate)
-
-        # stochastic depth
-        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule
-
-        # build Residual Swin Transformer blocks (RSTB)
-        self.layers = nn.ModuleList()
-        for i_layer in range(self.num_layers):
-            layer = RSTB(dim=embed_dim,
-                         input_resolution=(patches_resolution[0],
-                                           patches_resolution[1]),
-                         depth=depths[i_layer],
-                         num_heads=num_heads[i_layer],
-                         window_size=window_size,
-                         mlp_ratio=self.mlp_ratio,
-                         qkv_bias=qkv_bias, qk_scale=qk_scale,
-                         drop=drop_rate, attn_drop=attn_drop_rate,
-                         drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],  # no impact on SR results
-                         norm_layer=norm_layer,
-                         downsample=None,
-                         use_checkpoint=use_checkpoint,
-                         img_size=img_size,
-                         patch_size=patch_size,
-                         resi_connection=resi_connection
-
-                         )
-            self.layers.append(layer)
-        self.norm = norm_layer(self.num_features)
-
-        # build the last conv layer in deep feature extraction
-        if resi_connection == '1conv':
-            self.conv_after_body = nn.Conv2d(embed_dim, embed_dim, 3, 1, 1)
-        elif resi_connection == '3conv':
-            # to save parameters and memory
-            self.conv_after_body = nn.Sequential(nn.Conv2d(embed_dim, embed_dim // 4, 3, 1, 1),
-                                                 nn.LeakyReLU(negative_slope=0.2, inplace=True),
-                                                 nn.Conv2d(embed_dim // 4, embed_dim // 4, 1, 1, 0),
-                                                 nn.LeakyReLU(negative_slope=0.2, inplace=True),
-                                                 nn.Conv2d(embed_dim // 4, embed_dim, 3, 1, 1))
-
-        #####################################################################################################
-        ################################ 3, high quality image reconstruction ################################
-        if self.upsampler == 'pixelshuffle':
-            # for classical SR
-            self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
-                                                      nn.LeakyReLU(inplace=True))
-            self.upsample = Upsample(upscale, num_feat)
-            self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
-        elif self.upsampler == 'pixelshuffledirect':
-            # for lightweight SR (to save parameters)
-            self.upsample = UpsampleOneStep(upscale, embed_dim, num_out_ch,
-                                            (patches_resolution[0], patches_resolution[1]))
-        elif self.upsampler == 'nearest+conv':
-            # for real-world SR (less artifacts)
-            self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
-                                                      nn.LeakyReLU(inplace=True))
-            self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
-            if self.upscale == 4:
-                self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
-            self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
-            self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
-            self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
-        else:
-            # for image denoising and JPEG compression artifact reduction
-            self.conv_last = nn.Conv2d(embed_dim, num_out_ch, 3, 1, 1)
-
-        self.apply(self._init_weights)
-
-    def _init_weights(self, m):
-        if isinstance(m, nn.Linear):
-            trunc_normal_(m.weight, std=.02)
-            if isinstance(m, nn.Linear) and m.bias is not None:
-                nn.init.constant_(m.bias, 0)
-        elif isinstance(m, nn.LayerNorm):
-            nn.init.constant_(m.bias, 0)
-            nn.init.constant_(m.weight, 1.0)
-
-    @torch.jit.ignore
-    def no_weight_decay(self):
-        return {'absolute_pos_embed'}
-
-    @torch.jit.ignore
-    def no_weight_decay_keywords(self):
-        return {'relative_position_bias_table'}
-
-    def check_image_size(self, x):
-        _, _, h, w = x.size()
-        mod_pad_h = (self.window_size - h % self.window_size) % self.window_size
-        mod_pad_w = (self.window_size - w % self.window_size) % self.window_size
-        x = F.pad(x, (0, mod_pad_w, 0, mod_pad_h), 'reflect')
-        return x
-
-    def forward_features(self, x):
-        x_size = (x.shape[2], x.shape[3])
-        x = self.patch_embed(x)
-        if self.ape:
-            x = x + self.absolute_pos_embed
-        x = self.pos_drop(x)
-
-        for layer in self.layers:
-            x = layer(x, x_size)
-
-        x = self.norm(x)  # B L C
-        x = self.patch_unembed(x, x_size)
-
-        return x
-
-    def forward(self, x):
-        H, W = x.shape[2:]
-        x = self.check_image_size(x)
-
-        self.mean = self.mean.type_as(x)
-        x = (x - self.mean) * self.img_range
-
-        if self.upsampler == 'pixelshuffle':
-            # for classical SR
-            x = self.conv_first(x)
-            x = self.conv_after_body(self.forward_features(x)) + x
-            x = self.conv_before_upsample(x)
-            x = self.conv_last(self.upsample(x))
-        elif self.upsampler == 'pixelshuffledirect':
-            # for lightweight SR
-            x = self.conv_first(x)
-            x = self.conv_after_body(self.forward_features(x)) + x
-            x = self.upsample(x)
-        elif self.upsampler == 'nearest+conv':
-            # for real-world SR
-            x = self.conv_first(x)
-            x = self.conv_after_body(self.forward_features(x)) + x
-            x = self.conv_before_upsample(x)
-            x = self.lrelu(self.conv_up1(torch.nn.functional.interpolate(x, scale_factor=2, mode='nearest')))
-            if self.upscale == 4:
-                x = self.lrelu(self.conv_up2(torch.nn.functional.interpolate(x, scale_factor=2, mode='nearest')))
-            x = self.conv_last(self.lrelu(self.conv_hr(x)))
-        else:
-            # for image denoising and JPEG compression artifact reduction
-            x_first = self.conv_first(x)
-            res = self.conv_after_body(self.forward_features(x_first)) + x_first
-            x = x + self.conv_last(res)
-
-        x = x / self.img_range + self.mean
-
-        return x[:, :, :H*self.upscale, :W*self.upscale]
-
-    def flops(self):
-        flops = 0
-        H, W = self.patches_resolution
-        flops += H * W * 3 * self.embed_dim * 9
-        flops += self.patch_embed.flops()
-        for layer in self.layers:
-            flops += layer.flops()
-        flops += H * W * 3 * self.embed_dim * self.embed_dim
-        flops += self.upsample.flops()
-        return flops
-
-
-if __name__ == '__main__':
-    upscale = 4
-    window_size = 8
-    height = (1024 // upscale // window_size + 1) * window_size
-    width = (720 // upscale // window_size + 1) * window_size
-    model = SwinIR(upscale=2, img_size=(height, width),
-                   window_size=window_size, img_range=1., depths=[6, 6, 6, 6],
-                   embed_dim=60, num_heads=[6, 6, 6, 6], mlp_ratio=2, upsampler='pixelshuffledirect')
-    print(model)
-    print(height, width, model.flops() / 1e9)
-
-    x = torch.randn((1, 3, height, width))
-    x = model(x)
-    print(x.shape)

extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js

@@ -29,6 +29,7 @@ onUiLoaded(async() => {
     });
 
     function getActiveTab(elements, all = false) {
+        if (!elements.img2imgTabs) return null;
         const tabs = elements.img2imgTabs.querySelectorAll("button");
 
         if (all) return tabs;
@@ -43,6 +44,7 @@ onUiLoaded(async() => {
     // Get tab ID
     function getTabId(elements) {
         const activeTab = getActiveTab(elements);
+        if (!activeTab) return null;
         return tabNameToElementId[activeTab.innerText];
     }
 
@@ -218,6 +220,8 @@ onUiLoaded(async() => {
         canvas_hotkey_fullscreen: "KeyS",
         canvas_hotkey_move: "KeyF",
         canvas_hotkey_overlap: "KeyO",
+        canvas_hotkey_shrink_brush: "KeyQ",
+        canvas_hotkey_grow_brush: "KeyW",
         canvas_disabled_functions: [],
         canvas_show_tooltip: true,
         canvas_auto_expand: true,
@@ -227,6 +231,8 @@ onUiLoaded(async() => {
     const functionMap = {
         "Zoom": "canvas_hotkey_zoom",
         "Adjust brush size": "canvas_hotkey_adjust",
+        "Hotkey shrink brush": "canvas_hotkey_shrink_brush",
+        "Hotkey enlarge brush": "canvas_hotkey_grow_brush",
         "Moving canvas": "canvas_hotkey_move",
         "Fullscreen": "canvas_hotkey_fullscreen",
         "Reset Zoom": "canvas_hotkey_reset",
@@ -248,6 +254,7 @@ onUiLoaded(async() => {
     let isMoving = false;
     let mouseX, mouseY;
     let activeElement;
+    let interactedWithAltKey = false;
 
     const elements = Object.fromEntries(
         Object.keys(elementIDs).map(id => [
@@ -273,7 +280,7 @@ onUiLoaded(async() => {
         const targetElement = gradioApp().querySelector(elemId);
 
         if (!targetElement) {
-            console.log("Element not found");
+            console.log("Element not found", elemId);
             return;
         }
 
@@ -288,7 +295,7 @@ onUiLoaded(async() => {
 
         // Create tooltip
         function createTooltip() {
-            const toolTipElemnt =
+            const toolTipElement =
                 targetElement.querySelector(".image-container");
             const tooltip = document.createElement("div");
             tooltip.className = "canvas-tooltip";
@@ -351,7 +358,7 @@ onUiLoaded(async() => {
             tooltip.appendChild(tooltipContent);
 
             // Add a hint element to the target element
-            toolTipElemnt.appendChild(tooltip);
+            toolTipElement.appendChild(tooltip);
         }
 
         //Show tool tip if setting enable
@@ -361,9 +368,9 @@ onUiLoaded(async() => {
 
         // In the course of research, it was found that the tag img is very harmful when zooming and creates white canvases. This hack allows you to almost never think about this problem, it has no effect on webui.
         function fixCanvas() {
-            const activeTab = getActiveTab(elements).textContent.trim();
+            const activeTab = getActiveTab(elements)?.textContent.trim();
 
-            if (activeTab !== "img2img") {
+            if (activeTab && activeTab !== "img2img") {
                 const img = targetElement.querySelector(`${elemId} img`);
 
                 if (img && img.style.display !== "none") {
@@ -504,6 +511,10 @@ onUiLoaded(async() => {
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
                 e.preventDefault();
 
+                if (hotkeysConfig.canvas_hotkey_zoom === "Alt") {
+                    interactedWithAltKey = true;
+                }
+
                 let zoomPosX, zoomPosY;
                 let delta = 0.2;
                 if (elemData[elemId].zoomLevel > 7) {
@@ -686,7 +697,9 @@ onUiLoaded(async() => {
             const hotkeyActions = {
                 [hotkeysConfig.canvas_hotkey_reset]: resetZoom,
                 [hotkeysConfig.canvas_hotkey_overlap]: toggleOverlap,
-                [hotkeysConfig.canvas_hotkey_fullscreen]: fitToScreen
+                [hotkeysConfig.canvas_hotkey_fullscreen]: fitToScreen,
+                [hotkeysConfig.canvas_hotkey_shrink_brush]: () => adjustBrushSize(elemId, 10),
+                [hotkeysConfig.canvas_hotkey_grow_brush]: () => adjustBrushSize(elemId, -10)
             };
 
             const action = hotkeyActions[event.code];
@@ -777,23 +790,29 @@ onUiLoaded(async() => {
         targetElement.addEventListener("mouseleave", handleMouseLeave);
 
         // Reset zoom when click on another tab
-        elements.img2imgTabs.addEventListener("click", resetZoom);
-        elements.img2imgTabs.addEventListener("click", () => {
-            // targetElement.style.width = "";
-            if (parseInt(targetElement.style.width) > 865) {
-                setTimeout(fitToElement, 0);
-            }
-        });
+        if (elements.img2imgTabs) {
+            elements.img2imgTabs.addEventListener("click", resetZoom);
+            elements.img2imgTabs.addEventListener("click", () => {
+                // targetElement.style.width = "";
+                if (parseInt(targetElement.style.width) > 865) {
+                    setTimeout(fitToElement, 0);
+                }
+            });
+        }
 
         targetElement.addEventListener("wheel", e => {
             // change zoom level
-            const operation = e.deltaY > 0 ? "-" : "+";
+            const operation = (e.deltaY || -e.wheelDelta) > 0 ? "-" : "+";
             changeZoomLevel(operation, e);
 
             // Handle brush size adjustment with ctrl key pressed
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
                 e.preventDefault();
 
+                if (hotkeysConfig.canvas_hotkey_adjust === "Alt") {
+                    interactedWithAltKey = true;
+                }
+
                 // Increase or decrease brush size based on scroll direction
                 adjustBrushSize(elemId, e.deltaY);
             }
@@ -833,6 +852,20 @@ onUiLoaded(async() => {
         document.addEventListener("keydown", handleMoveKeyDown);
         document.addEventListener("keyup", handleMoveKeyUp);
 
+
+        // Prevent firefox from opening main menu when alt is used as a hotkey for zoom or brush size
+        function handleAltKeyUp(e) {
+            if (e.key !== "Alt" || !interactedWithAltKey) {
+                return;
+            }
+
+            e.preventDefault();
+            interactedWithAltKey = false;
+        }
+
+        document.addEventListener("keyup", handleAltKeyUp);
+
+
         // Detect zoom level and update the pan speed.
         function updatePanPosition(movementX, movementY) {
             let panSpeed = 2;

extensions-builtin/canvas-zoom-and-pan/scripts/hotkey_config.py

@@ -4,12 +4,14 @@ from modules import shared
 shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas Hotkeys"), {
     "canvas_hotkey_zoom": shared.OptionInfo("Alt", "Zoom canvas", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
     "canvas_hotkey_adjust": shared.OptionInfo("Ctrl", "Adjust brush size", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
+    "canvas_hotkey_shrink_brush": shared.OptionInfo("Q", "Shrink the brush size"),
+    "canvas_hotkey_grow_brush": shared.OptionInfo("W", "Enlarge the brush size"),
     "canvas_hotkey_move": shared.OptionInfo("F", "Moving the canvas").info("To work correctly in firefox, turn off 'Automatically search the page text when typing' in the browser settings"),
     "canvas_hotkey_fullscreen": shared.OptionInfo("S", "Fullscreen Mode, maximizes the picture so that it fits into the screen and stretches it to its full width "),
-    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas positon"),
-    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, neededs for testing"),
+    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas position"),
+    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, needed for testing"),
     "canvas_show_tooltip": shared.OptionInfo(True, "Enable tooltip on the canvas"),
     "canvas_auto_expand": shared.OptionInfo(True, "Automatically expands an image that does not fit completely in the canvas area, similar to manually pressing the S and R buttons"),
     "canvas_blur_prompt": shared.OptionInfo(False, "Take the focus off the prompt when working with a canvas"),
-    "canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size", "Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
+    "canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size","Hotkey enlarge brush","Hotkey shrink brush","Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
 }))

extensions-builtin/extra-options-section/scripts/extra_options_section.py

@@ -1,7 +1,7 @@
 import math
 
 import gradio as gr
-from modules import scripts, shared, ui_components, ui_settings, generation_parameters_copypaste
+from modules import scripts, shared, ui_components, ui_settings, infotext_utils, errors
 from modules.ui_components import FormColumn
 
 
@@ -23,11 +23,12 @@ class ExtraOptionsSection(scripts.Script):
         self.setting_names = []
         self.infotext_fields = []
         extra_options = shared.opts.extra_options_img2img if is_img2img else shared.opts.extra_options_txt2img
+        elem_id_tabname = "extra_options_" + ("img2img" if is_img2img else "txt2img")
 
-        mapping = {k: v for v, k in generation_parameters_copypaste.infotext_to_setting_name_mapping}
+        mapping = {k: v for v, k in infotext_utils.infotext_to_setting_name_mapping}
 
         with gr.Blocks() as interface:
-            with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and extra_options else gr.Group():
+            with gr.Accordion("Options", open=False, elem_id=elem_id_tabname) if shared.opts.extra_options_accordion and extra_options else gr.Group(elem_id=elem_id_tabname):
 
                 row_count = math.ceil(len(extra_options) / shared.opts.extra_options_cols)
 
@@ -41,7 +42,11 @@ class ExtraOptionsSection(scripts.Script):
                             setting_name = extra_options[index]
 
                             with FormColumn():
-                                comp = ui_settings.create_setting_component(setting_name)
+                                try:
+                                    comp = ui_settings.create_setting_component(setting_name)
+                                except KeyError:
+                                    errors.report(f"Can't add extra options for {setting_name} in ui")
+                                    continue
 
                             self.comps.append(comp)
                             self.setting_names.append(setting_name)
@@ -70,7 +75,7 @@ This page allows you to add some settings to the main interface of txt2img and i
 """),
     "extra_options_txt2img": shared.OptionInfo([], "Settings for txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
     "extra_options_img2img": shared.OptionInfo([], "Settings for img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
-    "extra_options_cols": shared.OptionInfo(1, "Number of columns for added settings", gr.Number, {"precision": 0}).needs_reload_ui(),
+    "extra_options_cols": shared.OptionInfo(1, "Number of columns for added settings", gr.Slider, {"step": 1, "minimum": 1, "maximum": 20}).info("displayed amount will depend on the actual browser window width").needs_reload_ui(),
     "extra_options_accordion": shared.OptionInfo(False, "Place added settings into an accordion").needs_reload_ui()
 }))
 

extensions-builtin/hypertile/scripts/hypertile_script.py

@@ -1,6 +1,5 @@
 import hypertile
 from modules import scripts, script_callbacks, shared
-from scripts.hypertile_xyz import add_axis_options
 
 
 class ScriptHypertile(scripts.Script):
@@ -17,11 +16,42 @@ class ScriptHypertile(scripts.Script):
 
         configure_hypertile(p.width, p.height, enable_unet=shared.opts.hypertile_enable_unet)
 
+        self.add_infotext(p)
+
     def before_hr(self, p, *args):
+
+        enable = shared.opts.hypertile_enable_unet_secondpass or shared.opts.hypertile_enable_unet
+
         # exclusive hypertile seed for the second pass
-        if not shared.opts.hypertile_enable_unet:
+        if enable:
             hypertile.set_hypertile_seed(p.all_seeds[0])
-        configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=shared.opts.hypertile_enable_unet_secondpass)
+
+        configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=enable)
+
+        if enable and not shared.opts.hypertile_enable_unet:
+            p.extra_generation_params["Hypertile U-Net second pass"] = True
+
+            self.add_infotext(p, add_unet_params=True)
+
+    def add_infotext(self, p, add_unet_params=False):
+        def option(name):
+            value = getattr(shared.opts, name)
+            default_value = shared.opts.get_default(name)
+            return None if value == default_value else value
+
+        if shared.opts.hypertile_enable_unet:
+            p.extra_generation_params["Hypertile U-Net"] = True
+
+        if shared.opts.hypertile_enable_unet or add_unet_params:
+            p.extra_generation_params["Hypertile U-Net max depth"] = option('hypertile_max_depth_unet')
+            p.extra_generation_params["Hypertile U-Net max tile size"] = option('hypertile_max_tile_unet')
+            p.extra_generation_params["Hypertile U-Net swap size"] = option('hypertile_swap_size_unet')
+
+        if shared.opts.hypertile_enable_vae:
+            p.extra_generation_params["Hypertile VAE"] = True
+            p.extra_generation_params["Hypertile VAE max depth"] = option('hypertile_max_depth_vae')
+            p.extra_generation_params["Hypertile VAE max tile size"] = option('hypertile_max_tile_vae')
+            p.extra_generation_params["Hypertile VAE swap size"] = option('hypertile_swap_size_vae')
 
 
 def configure_hypertile(width, height, enable_unet=True):
@@ -57,16 +87,15 @@ def on_ui_settings():
     benefit.
     """),
 
-        "hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net").info("noticeable change in details of the generated picture; if enabled, overrides the setting below"),
-        "hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass"),
-        "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
-        "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
-        "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-net swap size", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}),
-
-        "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE").info("minimal change in the generated picture"),
-        "hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
-        "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
-        "hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}),
+        "hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net", infotext="Hypertile U-Net").info("enables hypertile for all modes, including hires fix second pass; noticeable change in details of the generated picture"),
+        "hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass", infotext="Hypertile U-Net second pass").info("enables hypertile just for hires fix second pass - regardless of whether the above setting is enabled"),
+        "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile U-Net max depth").info("larger = more neural network layers affected; minor effect on performance"),
+        "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-Net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile U-Net max tile size").info("larger = worse performance"),
+        "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-Net swap size", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile U-Net swap size"),
+        "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE", infotext="Hypertile VAE").info("minimal change in the generated picture"),
+        "hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile VAE max depth"),
+        "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile VAE max tile size"),
+        "hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile VAE swap size"),
     }
 
     for name, opt in options.items():
@@ -74,5 +103,20 @@ def on_ui_settings():
         shared.opts.add_option(name, opt)
 
 
+def add_axis_options():
+    xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
+    xyz_grid.axis_options.extend([
+        xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet_secondpass', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_unet"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] Unet Max Depth'), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_unet"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] Unet Max Tile Size')),
+        xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_unet"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] Unet Swap Size')),
+        xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, xyz_grid.apply_override('hypertile_enable_vae', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_vae"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] VAE Max Depth'), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_vae"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] VAE Max Tile Size')),
+        xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_vae"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] VAE Swap Size')),
+    ])
+
+
 script_callbacks.on_ui_settings(on_ui_settings)
 script_callbacks.on_before_ui(add_axis_options)

extensions-builtin/hypertile/scripts/hypertile_xyz.py

@@ -1,51 +0,0 @@
-from modules import scripts
-from modules.shared import opts
-
-xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
-
-def int_applier(value_name:str, min_range:int = -1, max_range:int = -1):
-    """
-    Returns a function that applies the given value to the given value_name in opts.data.
-    """
-    def validate(value_name:str, value:str):
-        value = int(value)
-        # validate value
-        if not min_range == -1:
-            assert value >= min_range, f"Value {value} for {value_name} must be greater than or equal to {min_range}"
-        if not max_range == -1:
-            assert value <= max_range, f"Value {value} for {value_name} must be less than or equal to {max_range}"
-    def apply_int(p, x, xs):
-        validate(value_name, x)
-        opts.data[value_name] = int(x)
-    return apply_int
-
-def bool_applier(value_name:str):
-    """
-    Returns a function that applies the given value to the given value_name in opts.data.
-    """
-    def validate(value_name:str, value:str):
-        assert value.lower() in ["true", "false"], f"Value {value} for {value_name} must be either true or false"
-    def apply_bool(p, x, xs):
-        validate(value_name, x)
-        value_boolean = x.lower() == "true"
-        opts.data[value_name] = value_boolean
-    return apply_bool
-
-def add_axis_options():
-    extra_axis_options = [
-        xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, bool_applier("hypertile_enable_unet"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, bool_applier("hypertile_enable_unet_secondpass"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, int_applier("hypertile_max_depth_unet", 0, 3), choices=lambda: [str(x) for x in range(4)]),
-        xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, int_applier("hypertile_max_tile_unet", 0, 512)),
-        xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, int_applier("hypertile_swap_size_unet", 0, 64)),
-        xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, bool_applier("hypertile_enable_vae"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, int_applier("hypertile_max_depth_vae", 0, 3), choices=lambda: [str(x) for x in range(4)]),
-        xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, int_applier("hypertile_max_tile_vae", 0, 512)),
-        xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, int_applier("hypertile_swap_size_vae", 0, 64)),
-    ]
-    set_a = {opt.label for opt in xyz_grid.axis_options}
-    set_b = {opt.label for opt in extra_axis_options}
-    if set_a.intersection(set_b):
-        return
-
-    xyz_grid.axis_options.extend(extra_axis_options)

extensions-builtin/postprocessing-for-training/scripts/postprocessing_autosized_crop.py

@@ -28,7 +28,7 @@ def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, thr
 
 class ScriptPostprocessingAutosizedCrop(scripts_postprocessing.ScriptPostprocessing):
     name = "Auto-sized crop"
-    order = 4000
+    order = 4020
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Auto-sized crop") as enable:

extensions-builtin/postprocessing-for-training/scripts/postprocessing_caption.py

@@ -4,7 +4,7 @@ import gradio as gr
 
 class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing):
     name = "Caption"
-    order = 4000
+    order = 4040
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Caption") as enable:
@@ -25,6 +25,6 @@ class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing):
             captions.append(deepbooru.model.tag(pp.image))
 
         if "BLIP" in option:
-            captions.append(shared.interrogator.generate_caption(pp.image))
+            captions.append(shared.interrogator.interrogate(pp.image.convert("RGB")))
 
         pp.caption = ", ".join([x for x in captions if x])

extensions-builtin/postprocessing-for-training/scripts/postprocessing_create_flipped_copies.py

@@ -6,7 +6,7 @@ import gradio as gr
 
 class ScriptPostprocessingCreateFlippedCopies(scripts_postprocessing.ScriptPostprocessing):
     name = "Create flipped copies"
-    order = 4000
+    order = 4030
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Create flipped copies") as enable:

extensions-builtin/postprocessing-for-training/scripts/postprocessing_focal_crop.py

@@ -7,7 +7,7 @@ from modules.textual_inversion import autocrop
 
 class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing):
     name = "Auto focal point crop"
-    order = 4000
+    order = 4010
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Auto focal point crop") as enable:

extensions-builtin/postprocessing-for-training/scripts/postprocessing_split_oversized.py

@@ -61,7 +61,7 @@ class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostproces
             ratio = (pp.image.height * width) / (pp.image.width * height)
             inverse_xy = True
 
-        if ratio >= 1.0 and ratio > split_threshold:
+        if ratio >= 1.0 or ratio > split_threshold:
             return
 
         result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio)

extensions-builtin/soft-inpainting/scripts/soft_inpainting.py

@@ -0,0 +1,760 @@
+import numpy as np
+import gradio as gr
+import math
+from modules.ui_components import InputAccordion
+import modules.scripts as scripts
+from modules.torch_utils import float64
+
+
+class SoftInpaintingSettings:
+    def __init__(self,
+                 mask_blend_power,
+                 mask_blend_scale,
+                 inpaint_detail_preservation,
+                 composite_mask_influence,
+                 composite_difference_threshold,
+                 composite_difference_contrast):
+        self.mask_blend_power = mask_blend_power
+        self.mask_blend_scale = mask_blend_scale
+        self.inpaint_detail_preservation = inpaint_detail_preservation
+        self.composite_mask_influence = composite_mask_influence
+        self.composite_difference_threshold = composite_difference_threshold
+        self.composite_difference_contrast = composite_difference_contrast
+
+    def add_generation_params(self, dest):
+        dest[enabled_gen_param_label] = True
+        dest[gen_param_labels.mask_blend_power] = self.mask_blend_power
+        dest[gen_param_labels.mask_blend_scale] = self.mask_blend_scale
+        dest[gen_param_labels.inpaint_detail_preservation] = self.inpaint_detail_preservation
+        dest[gen_param_labels.composite_mask_influence] = self.composite_mask_influence
+        dest[gen_param_labels.composite_difference_threshold] = self.composite_difference_threshold
+        dest[gen_param_labels.composite_difference_contrast] = self.composite_difference_contrast
+
+
+# ------------------- Methods -------------------
+
+def processing_uses_inpainting(p):
+    # TODO: Figure out a better way to determine if inpainting is being used by p
+    if getattr(p, "image_mask", None) is not None:
+        return True
+
+    if getattr(p, "mask", None) is not None:
+        return True
+
+    if getattr(p, "nmask", None) is not None:
+        return True
+
+    return False
+
+
+def latent_blend(settings, a, b, t):
+    """
+    Interpolates two latent image representations according to the parameter t,
+    where the interpolated vectors' magnitudes are also interpolated separately.
+    The "detail_preservation" factor biases the magnitude interpolation towards
+    the larger of the two magnitudes.
+    """
+    import torch
+
+    # NOTE: We use inplace operations wherever possible.
+
+    if len(t.shape) == 3:
+        # [4][w][h] to [1][4][w][h]
+        t2 = t.unsqueeze(0)
+        # [4][w][h] to [1][1][w][h] - the [4] seem redundant.
+        t3 = t[0].unsqueeze(0).unsqueeze(0)
+    else:
+        t2 = t
+        t3 = t[:, 0][:, None]
+
+    one_minus_t2 = 1 - t2
+    one_minus_t3 = 1 - t3
+
+    # Linearly interpolate the image vectors.
+    a_scaled = a * one_minus_t2
+    b_scaled = b * t2
+    image_interp = a_scaled
+    image_interp.add_(b_scaled)
+    result_type = image_interp.dtype
+    del a_scaled, b_scaled, t2, one_minus_t2
+
+    # Calculate the magnitude of the interpolated vectors. (We will remove this magnitude.)
+    # 64-bit operations are used here to allow large exponents.
+    current_magnitude = torch.norm(image_interp, p=2, dim=1, keepdim=True).to(float64(image_interp)).add_(0.00001)
+
+    # Interpolate the powered magnitudes, then un-power them (bring them back to a power of 1).
+    a_magnitude = torch.norm(a, p=2, dim=1, keepdim=True).to(float64(a)).pow_(settings.inpaint_detail_preservation) * one_minus_t3
+    b_magnitude = torch.norm(b, p=2, dim=1, keepdim=True).to(float64(b)).pow_(settings.inpaint_detail_preservation) * t3
+    desired_magnitude = a_magnitude
+    desired_magnitude.add_(b_magnitude).pow_(1 / settings.inpaint_detail_preservation)
+    del a_magnitude, b_magnitude, t3, one_minus_t3
+
+    # Change the linearly interpolated image vectors' magnitudes to the value we want.
+    # This is the last 64-bit operation.
+    image_interp_scaling_factor = desired_magnitude
+    image_interp_scaling_factor.div_(current_magnitude)
+    image_interp_scaling_factor = image_interp_scaling_factor.to(result_type)
+    image_interp_scaled = image_interp
+    image_interp_scaled.mul_(image_interp_scaling_factor)
+    del current_magnitude
+    del desired_magnitude
+    del image_interp
+    del image_interp_scaling_factor
+    del result_type
+
+    return image_interp_scaled
+
+
+def get_modified_nmask(settings, nmask, sigma):
+    """
+    Converts a negative mask representing the transparency of the original latent vectors being overlaid
+    to a mask that is scaled according to the denoising strength for this step.
+
+    Where:
+        0 = fully opaque, infinite density, fully masked
+        1 = fully transparent, zero density, fully unmasked
+
+    We bring this transparency to a power, as this allows one to simulate N number of blending operations
+    where N can be any positive real value. Using this one can control the balance of influence between
+    the denoiser and the original latents according to the sigma value.
+
+    NOTE: "mask" is not used
+    """
+    import torch
+    return torch.pow(nmask, (sigma ** settings.mask_blend_power) * settings.mask_blend_scale)
+
+
+def apply_adaptive_masks(
+        settings: SoftInpaintingSettings,
+        nmask,
+        latent_orig,
+        latent_processed,
+        overlay_images,
+        width, height,
+        paste_to):
+    import torch
+    import modules.processing as proc
+    import modules.images as images
+    from PIL import Image, ImageOps, ImageFilter
+
+    # TODO: Bias the blending according to the latent mask, add adjustable parameter for bias control.
+    if len(nmask.shape) == 3:
+        latent_mask = nmask[0].float()
+    else:
+        latent_mask = nmask[:, 0].float()
+    # convert the original mask into a form we use to scale distances for thresholding
+    mask_scalar = 1 - (torch.clamp(latent_mask, min=0, max=1) ** (settings.mask_blend_scale / 2))
+    mask_scalar = (0.5 * (1 - settings.composite_mask_influence)
+                   + mask_scalar * settings.composite_mask_influence)
+    mask_scalar = mask_scalar / (1.00001 - mask_scalar)
+    mask_scalar = mask_scalar.cpu().numpy()
+
+    latent_distance = torch.norm(latent_processed - latent_orig, p=2, dim=1)
+
+    kernel, kernel_center = get_gaussian_kernel(stddev_radius=1.5, max_radius=2)
+
+    masks_for_overlay = []
+
+    for i, (distance_map, overlay_image) in enumerate(zip(latent_distance, overlay_images)):
+        converted_mask = distance_map.float().cpu().numpy()
+        converted_mask = weighted_histogram_filter(converted_mask, kernel, kernel_center,
+                                                   percentile_min=0.9, percentile_max=1, min_width=1)
+        converted_mask = weighted_histogram_filter(converted_mask, kernel, kernel_center,
+                                                   percentile_min=0.25, percentile_max=0.75, min_width=1)
+
+        # The distance at which opacity of original decreases to 50%
+        if len(mask_scalar.shape) == 3:
+            if mask_scalar.shape[0] > i:
+                half_weighted_distance = settings.composite_difference_threshold * mask_scalar[i]
+            else:
+                half_weighted_distance = settings.composite_difference_threshold * mask_scalar[0]
+        else:
+            half_weighted_distance = settings.composite_difference_threshold * mask_scalar
+
+        converted_mask = converted_mask / half_weighted_distance
+
+        converted_mask = 1 / (1 + converted_mask ** settings.composite_difference_contrast)
+        converted_mask = smootherstep(converted_mask)
+        converted_mask = 1 - converted_mask
+        converted_mask = 255. * converted_mask
+        converted_mask = converted_mask.astype(np.uint8)
+        converted_mask = Image.fromarray(converted_mask)
+        converted_mask = images.resize_image(2, converted_mask, width, height)
+        converted_mask = proc.create_binary_mask(converted_mask, round=False)
+
+        # Remove aliasing artifacts using a gaussian blur.
+        converted_mask = converted_mask.filter(ImageFilter.GaussianBlur(radius=4))
+
+        # Expand the mask to fit the whole image if needed.
+        if paste_to is not None:
+            converted_mask = proc.uncrop(converted_mask,
+                                         (overlay_image.width, overlay_image.height),
+                                         paste_to)
+
+        masks_for_overlay.append(converted_mask)
+
+        image_masked = Image.new('RGBa', (overlay_image.width, overlay_image.height))
+        image_masked.paste(overlay_image.convert("RGBA").convert("RGBa"),
+                           mask=ImageOps.invert(converted_mask.convert('L')))
+
+        overlay_images[i] = image_masked.convert('RGBA')
+
+    return masks_for_overlay
+
+
+def apply_masks(
+        settings,
+        nmask,
+        overlay_images,
+        width, height,
+        paste_to):
+    import torch
+    import modules.processing as proc
+    import modules.images as images
+    from PIL import Image, ImageOps, ImageFilter
+
+    converted_mask = nmask[0].float()
+    converted_mask = torch.clamp(converted_mask, min=0, max=1).pow_(settings.mask_blend_scale / 2)
+    converted_mask = 255. * converted_mask
+    converted_mask = converted_mask.cpu().numpy().astype(np.uint8)
+    converted_mask = Image.fromarray(converted_mask)
+    converted_mask = images.resize_image(2, converted_mask, width, height)
+    converted_mask = proc.create_binary_mask(converted_mask, round=False)
+
+    # Remove aliasing artifacts using a gaussian blur.
+    converted_mask = converted_mask.filter(ImageFilter.GaussianBlur(radius=4))
+
+    # Expand the mask to fit the whole image if needed.
+    if paste_to is not None:
+        converted_mask = proc.uncrop(converted_mask,
+                                     (width, height),
+                                     paste_to)
+
+    masks_for_overlay = []
+
+    for i, overlay_image in enumerate(overlay_images):
+        masks_for_overlay[i] = converted_mask
+
+        image_masked = Image.new('RGBa', (overlay_image.width, overlay_image.height))
+        image_masked.paste(overlay_image.convert("RGBA").convert("RGBa"),
+                           mask=ImageOps.invert(converted_mask.convert('L')))
+
+        overlay_images[i] = image_masked.convert('RGBA')
+
+    return masks_for_overlay
+
+
+def weighted_histogram_filter(img, kernel, kernel_center, percentile_min=0.0, percentile_max=1.0, min_width=1.0):
+    """
+    Generalization convolution filter capable of applying
+    weighted mean, median, maximum, and minimum filters
+    parametrically using an arbitrary kernel.
+
+    Args:
+        img (nparray):
+            The image, a 2-D array of floats, to which the filter is being applied.
+        kernel (nparray):
+            The kernel, a 2-D array of floats.
+        kernel_center (nparray):
+            The kernel center coordinate, a 1-D array with two elements.
+        percentile_min (float):
+            The lower bound of the histogram window used by the filter,
+            from 0 to 1.
+        percentile_max (float):
+            The upper bound of the histogram window used by the filter,
+            from 0 to 1.
+        min_width (float):
+            The minimum size of the histogram window bounds, in weight units.
+            Must be greater than 0.
+
+    Returns:
+        (nparray): A filtered copy of the input image "img", a 2-D array of floats.
+    """
+
+    # Converts an index tuple into a vector.
+    def vec(x):
+        return np.array(x)
+
+    kernel_min = -kernel_center
+    kernel_max = vec(kernel.shape) - kernel_center
+
+    def weighted_histogram_filter_single(idx):
+        idx = vec(idx)
+        min_index = np.maximum(0, idx + kernel_min)
+        max_index = np.minimum(vec(img.shape), idx + kernel_max)
+        window_shape = max_index - min_index
+
+        class WeightedElement:
+            """
+            An element of the histogram, its weight
+            and bounds.
+            """
+
+            def __init__(self, value, weight):
+                self.value: float = value
+                self.weight: float = weight
+                self.window_min: float = 0.0
+                self.window_max: float = 1.0
+
+        # Collect the values in the image as WeightedElements,
+        # weighted by their corresponding kernel values.
+        values = []
+        for window_tup in np.ndindex(tuple(window_shape)):
+            window_index = vec(window_tup)
+            image_index = window_index + min_index
+            centered_kernel_index = image_index - idx
+            kernel_index = centered_kernel_index + kernel_center
+            element = WeightedElement(img[tuple(image_index)], kernel[tuple(kernel_index)])
+            values.append(element)
+
+        def sort_key(x: WeightedElement):
+            return x.value
+
+        values.sort(key=sort_key)
+
+        # Calculate the height of the stack (sum)
+        # and each sample's range they occupy in the stack
+        sum = 0
+        for i in range(len(values)):
+            values[i].window_min = sum
+            sum += values[i].weight
+            values[i].window_max = sum
+
+        # Calculate what range of this stack ("window")
+        # we want to get the weighted average across.
+        window_min = sum * percentile_min
+        window_max = sum * percentile_max
+        window_width = window_max - window_min
+
+        # Ensure the window is within the stack and at least a certain size.
+        if window_width < min_width:
+            window_center = (window_min + window_max) / 2
+            window_min = window_center - min_width / 2
+            window_max = window_center + min_width / 2
+
+            if window_max > sum:
+                window_max = sum
+                window_min = sum - min_width
+
+            if window_min < 0:
+                window_min = 0
+                window_max = min_width
+
+        value = 0
+        value_weight = 0
+
+        # Get the weighted average of all the samples
+        # that overlap with the window, weighted
+        # by the size of their overlap.
+        for i in range(len(values)):
+            if window_min >= values[i].window_max:
+                continue
+            if window_max <= values[i].window_min:
+                break
+
+            s = max(window_min, values[i].window_min)
+            e = min(window_max, values[i].window_max)
+            w = e - s
+
+            value += values[i].value * w
+            value_weight += w
+
+        return value / value_weight if value_weight != 0 else 0
+
+    img_out = img.copy()
+
+    # Apply the kernel operation over each pixel.
+    for index in np.ndindex(img.shape):
+        img_out[index] = weighted_histogram_filter_single(index)
+
+    return img_out
+
+
+def smoothstep(x):
+    """
+    The smoothstep function, input should be clamped to 0-1 range.
+    Turns a diagonal line (f(x) = x) into a sigmoid-like curve.
+    """
+    return x * x * (3 - 2 * x)
+
+
+def smootherstep(x):
+    """
+    The smootherstep function, input should be clamped to 0-1 range.
+    Turns a diagonal line (f(x) = x) into a sigmoid-like curve.
+    """
+    return x * x * x * (x * (6 * x - 15) + 10)
+
+
+def get_gaussian_kernel(stddev_radius=1.0, max_radius=2):
+    """
+    Creates a Gaussian kernel with thresholded edges.
+
+    Args:
+        stddev_radius (float):
+            Standard deviation of the gaussian kernel, in pixels.
+        max_radius (int):
+            The size of the filter kernel. The number of pixels is (max_radius*2+1) ** 2.
+            The kernel is thresholded so that any values one pixel beyond this radius
+            is weighted at 0.
+
+    Returns:
+        (nparray, nparray): A kernel array (shape: (N, N)), its center coordinate (shape: (2))
+    """
+
+    # Evaluates a 0-1 normalized gaussian function for a given square distance from the mean.
+    def gaussian(sqr_mag):
+        return math.exp(-sqr_mag / (stddev_radius * stddev_radius))
+
+    # Helper function for converting a tuple to an array.
+    def vec(x):
+        return np.array(x)
+
+    """
+    Since a gaussian is unbounded, we need to limit ourselves
+    to a finite range.
+    We taper the ends off at the end of that range so they equal zero
+    while preserving the maximum value of 1 at the mean.
+    """
+    zero_radius = max_radius + 1.0
+    gauss_zero = gaussian(zero_radius * zero_radius)
+    gauss_kernel_scale = 1 / (1 - gauss_zero)
+
+    def gaussian_kernel_func(coordinate):
+        x = coordinate[0] ** 2.0 + coordinate[1] ** 2.0
+        x = gaussian(x)
+        x -= gauss_zero
+        x *= gauss_kernel_scale
+        x = max(0.0, x)
+        return x
+
+    size = max_radius * 2 + 1
+    kernel_center = max_radius
+    kernel = np.zeros((size, size))
+
+    for index in np.ndindex(kernel.shape):
+        kernel[index] = gaussian_kernel_func(vec(index) - kernel_center)
+
+    return kernel, kernel_center
+
+
+# ------------------- Constants -------------------
+
+
+default = SoftInpaintingSettings(1, 0.5, 4, 0, 0.5, 2)
+
+enabled_ui_label = "Soft inpainting"
+enabled_gen_param_label = "Soft inpainting enabled"
+enabled_el_id = "soft_inpainting_enabled"
+
+ui_labels = SoftInpaintingSettings(
+    "Schedule bias",
+    "Preservation strength",
+    "Transition contrast boost",
+    "Mask influence",
+    "Difference threshold",
+    "Difference contrast")
+
+ui_info = SoftInpaintingSettings(
+    "Shifts when preservation of original content occurs during denoising.",
+    "How strongly partially masked content should be preserved.",
+    "Amplifies the contrast that may be lost in partially masked regions.",
+    "How strongly the original mask should bias the difference threshold.",
+    "How much an image region can change before the original pixels are not blended in anymore.",
+    "How sharp the transition should be between blended and not blended.")
+
+gen_param_labels = SoftInpaintingSettings(
+    "Soft inpainting schedule bias",
+    "Soft inpainting preservation strength",
+    "Soft inpainting transition contrast boost",
+    "Soft inpainting mask influence",
+    "Soft inpainting difference threshold",
+    "Soft inpainting difference contrast")
+
+el_ids = SoftInpaintingSettings(
+    "mask_blend_power",
+    "mask_blend_scale",
+    "inpaint_detail_preservation",
+    "composite_mask_influence",
+    "composite_difference_threshold",
+    "composite_difference_contrast")
+
+
+# ------------------- Script -------------------
+
+
+class Script(scripts.Script):
+    def __init__(self):
+        self.section = "inpaint"
+        self.masks_for_overlay = None
+        self.overlay_images = None
+
+    def title(self):
+        return "Soft Inpainting"
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible if is_img2img else False
+
+    def ui(self, is_img2img):
+        if not is_img2img:
+            return
+
+        with InputAccordion(False, label=enabled_ui_label, elem_id=enabled_el_id) as soft_inpainting_enabled:
+            with gr.Group():
+                gr.Markdown(
+                    """
+                    Soft inpainting allows you to **seamlessly blend original content with inpainted content** according to the mask opacity.
+                    **High _Mask blur_** values are recommended!
+                    """)
+
+                power = \
+                    gr.Slider(label=ui_labels.mask_blend_power,
+                              info=ui_info.mask_blend_power,
+                              minimum=0,
+                              maximum=8,
+                              step=0.1,
+                              value=default.mask_blend_power,
+                              elem_id=el_ids.mask_blend_power)
+                scale = \
+                    gr.Slider(label=ui_labels.mask_blend_scale,
+                              info=ui_info.mask_blend_scale,
+                              minimum=0,
+                              maximum=8,
+                              step=0.05,
+                              value=default.mask_blend_scale,
+                              elem_id=el_ids.mask_blend_scale)
+                detail = \
+                    gr.Slider(label=ui_labels.inpaint_detail_preservation,
+                              info=ui_info.inpaint_detail_preservation,
+                              minimum=1,
+                              maximum=32,
+                              step=0.5,
+                              value=default.inpaint_detail_preservation,
+                              elem_id=el_ids.inpaint_detail_preservation)
+
+                gr.Markdown(
+                    """
+                    ### Pixel Composite Settings
+                    """)
+
+                mask_inf = \
+                    gr.Slider(label=ui_labels.composite_mask_influence,
+                              info=ui_info.composite_mask_influence,
+                              minimum=0,
+                              maximum=1,
+                              step=0.05,
+                              value=default.composite_mask_influence,
+                              elem_id=el_ids.composite_mask_influence)
+
+                dif_thresh = \
+                    gr.Slider(label=ui_labels.composite_difference_threshold,
+                              info=ui_info.composite_difference_threshold,
+                              minimum=0,
+                              maximum=8,
+                              step=0.25,
+                              value=default.composite_difference_threshold,
+                              elem_id=el_ids.composite_difference_threshold)
+
+                dif_contr = \
+                    gr.Slider(label=ui_labels.composite_difference_contrast,
+                              info=ui_info.composite_difference_contrast,
+                              minimum=0,
+                              maximum=8,
+                              step=0.25,
+                              value=default.composite_difference_contrast,
+                              elem_id=el_ids.composite_difference_contrast)
+
+                with gr.Accordion("Help", open=False):
+                    gr.Markdown(
+                        f"""
+                        ### {ui_labels.mask_blend_power}
+
+                        The blending strength of original content is scaled proportionally with the decreasing noise level values at each step (sigmas).
+                        This ensures that the influence of the denoiser and original content preservation is roughly balanced at each step.
+                        This balance can be shifted using this parameter, controlling whether earlier or later steps have stronger preservation.
+
+                        - **Below 1**: Stronger preservation near the end (with low sigma)
+                        - **1**: Balanced (proportional to sigma)
+                        - **Above 1**: Stronger preservation in the beginning (with high sigma)
+                        """)
+                    gr.Markdown(
+                        f"""
+                        ### {ui_labels.mask_blend_scale}
+
+                        Skews whether partially masked image regions should be more likely to preserve the original content or favor inpainted content.
+                        This may need to be adjusted depending on the {ui_labels.mask_blend_power}, CFG Scale, prompt and Denoising strength.
+
+                        - **Low values**: Favors generated content.
+                        - **High values**: Favors original content.
+                        """)
+                    gr.Markdown(
+                        f"""
+                        ### {ui_labels.inpaint_detail_preservation}
+
+                        This parameter controls how the original latent vectors and denoised latent vectors are interpolated.
+                        With higher values, the magnitude of the resulting blended vector will be closer to the maximum of the two interpolated vectors.
+                        This can prevent the loss of contrast that occurs with linear interpolation.
+
+                        - **Low values**: Softer blending, details may fade.
+                        - **High values**: Stronger contrast, may over-saturate colors.
+                        """)
+
+                    gr.Markdown(
+                        """
+                        ## Pixel Composite Settings
+
+                        Masks are generated based on how much a part of the image changed after denoising.
+                        These masks are used to blend the original and final images together.
+                        If the difference is low, the original pixels are used instead of the pixels returned by the inpainting process.
+                        """)
+
+                    gr.Markdown(
+                        f"""
+                        ### {ui_labels.composite_mask_influence}
+
+                        This parameter controls how much the mask should bias this sensitivity to difference.
+
+                        - **0**: Ignore the mask, only consider differences in image content.
+                        - **1**: Follow the mask closely despite image content changes.
+                        """)
+
+                    gr.Markdown(
+                        f"""
+                        ### {ui_labels.composite_difference_threshold}
+
+                        This value represents the difference at which the original pixels will have less than 50% opacity.
+
+                        - **Low values**: Two images patches must be almost the same in order to retain original pixels.
+                        - **High values**: Two images patches can be very different and still retain original pixels.
+                        """)
+
+                    gr.Markdown(
+                        f"""
+                        ### {ui_labels.composite_difference_contrast}
+
+                        This value represents the contrast between the opacity of the original and inpainted content.
+
+                        - **Low values**: The blend will be more gradual and have longer transitions, but may cause ghosting.
+                        - **High values**: Ghosting will be less common, but transitions may be very sudden.
+                        """)
+
+        self.infotext_fields = [(soft_inpainting_enabled, enabled_gen_param_label),
+                                (power, gen_param_labels.mask_blend_power),
+                                (scale, gen_param_labels.mask_blend_scale),
+                                (detail, gen_param_labels.inpaint_detail_preservation),
+                                (mask_inf, gen_param_labels.composite_mask_influence),
+                                (dif_thresh, gen_param_labels.composite_difference_threshold),
+                                (dif_contr, gen_param_labels.composite_difference_contrast)]
+
+        self.paste_field_names = []
+        for _, field_name in self.infotext_fields:
+            self.paste_field_names.append(field_name)
+
+        return [soft_inpainting_enabled,
+                power,
+                scale,
+                detail,
+                mask_inf,
+                dif_thresh,
+                dif_contr]
+
+    def process(self, p, enabled, power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr):
+        if not enabled:
+            return
+
+        if not processing_uses_inpainting(p):
+            return
+
+        # Shut off the rounding it normally does.
+        p.mask_round = False
+
+        settings = SoftInpaintingSettings(power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr)
+
+        # p.extra_generation_params["Mask rounding"] = False
+        settings.add_generation_params(p.extra_generation_params)
+
+    def on_mask_blend(self, p, mba: scripts.MaskBlendArgs, enabled, power, scale, detail_preservation, mask_inf,
+                      dif_thresh, dif_contr):
+        if not enabled:
+            return
+
+        if not processing_uses_inpainting(p):
+            return
+
+        if mba.is_final_blend:
+            mba.blended_latent = mba.current_latent
+            return
+
+        settings = SoftInpaintingSettings(power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr)
+
+        # todo: Why is sigma 2D? Both values are the same.
+        mba.blended_latent = latent_blend(settings,
+                                          mba.init_latent,
+                                          mba.current_latent,
+                                          get_modified_nmask(settings, mba.nmask, mba.sigma[0]))
+
+    def post_sample(self, p, ps: scripts.PostSampleArgs, enabled, power, scale, detail_preservation, mask_inf,
+                    dif_thresh, dif_contr):
+        if not enabled:
+            return
+
+        if not processing_uses_inpainting(p):
+            return
+
+        nmask = getattr(p, "nmask", None)
+        if nmask is None:
+            return
+
+        from modules import images
+        from modules.shared import opts
+
+        settings = SoftInpaintingSettings(power, scale, detail_preservation, mask_inf, dif_thresh, dif_contr)
+
+        # since the original code puts holes in the existing overlay images,
+        # we have to rebuild them.
+        self.overlay_images = []
+        for img in p.init_images:
+
+            image = images.flatten(img, opts.img2img_background_color)
+
+            if p.paste_to is None and p.resize_mode != 3:
+                image = images.resize_image(p.resize_mode, image, p.width, p.height)
+
+            self.overlay_images.append(image.convert('RGBA'))
+
+        if len(p.init_images) == 1:
+            self.overlay_images = self.overlay_images * p.batch_size
+
+        if getattr(ps.samples, 'already_decoded', False):
+            self.masks_for_overlay = apply_masks(settings=settings,
+                                                 nmask=nmask,
+                                                 overlay_images=self.overlay_images,
+                                                 width=p.width,
+                                                 height=p.height,
+                                                 paste_to=p.paste_to)
+        else:
+            self.masks_for_overlay = apply_adaptive_masks(settings=settings,
+                                                          nmask=nmask,
+                                                          latent_orig=p.init_latent,
+                                                          latent_processed=ps.samples,
+                                                          overlay_images=self.overlay_images,
+                                                          width=p.width,
+                                                          height=p.height,
+                                                          paste_to=p.paste_to)
+
+    def postprocess_maskoverlay(self, p, ppmo: scripts.PostProcessMaskOverlayArgs, enabled, power, scale,
+                                detail_preservation, mask_inf, dif_thresh, dif_contr):
+        if not enabled:
+            return
+
+        if not processing_uses_inpainting(p):
+            return
+
+        if self.masks_for_overlay is None:
+            return
+
+        if self.overlay_images is None:
+            return
+
+        ppmo.mask_for_overlay = self.masks_for_overlay[ppmo.index]
+        ppmo.overlay_image = self.overlay_images[ppmo.index]

html/extra-networks-card.html

@@ -1,14 +1,9 @@
-<div class='card' style={style} onclick={card_clicked} data-name="{name}" {sort_keys}>
+<div class="card" style="{style}" onclick="{card_clicked}" data-name="{name}" {sort_keys}>
 	{background_image}
-	<div class="button-row">
-		{metadata_button}
-		{edit_button}
-	</div>
-	<div class='actions'>
-		<div class='additional'>
-			<span style="display:none" class='search_term{search_only}'>{search_term}</span>
-		</div>
-		<span class='name'>{name}</span>
-		<span class='description'>{description}</span>
+	<div class="button-row">{copy_path_button}{metadata_button}{edit_button}</div>
+	<div class="actions">
+		<div class="additional">{search_terms}</div>
+		<span class="name">{name}</span>
+		<span class="description">{description}</span>
 	</div>
 </div>

html/extra-networks-copy-path-button.html

@@ -0,0 +1,5 @@
+<div class="copy-path-button card-button"
+    title="Copy path to clipboard"
+    onclick="extraNetworksCopyCardPath(event)"
+    data-clipboard-text="{filename}">
+</div>

html/extra-networks-edit-item-button.html

@@ -0,0 +1,4 @@
+<div class="edit-button card-button"
+    title="Edit metadata"
+    onclick="extraNetworksEditUserMetadata(event, '{tabname}', '{extra_networks_tabname}')">
+</div>

html/extra-networks-metadata-button.html

@@ -0,0 +1,4 @@
+<div class="metadata-button card-button"
+    title="Show internal metadata"
+    onclick="extraNetworksRequestMetadata(event, '{extra_networks_tabname}')">
+</div>

html/extra-networks-pane-dirs.html

@@ -0,0 +1,8 @@
+    <div class="extra-network-pane-content-dirs">
+        <div id='{tabname}_{extra_networks_tabname}_dirs' class='extra-network-dirs'>
+            {dirs_html}
+        </div>
+        <div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards'>
+            {items_html}
+        </div>
+    </div>

html/extra-networks-pane-tree.html

@@ -0,0 +1,8 @@
+    <div class="extra-network-pane-content-tree resize-handle-row">
+        <div id='{tabname}_{extra_networks_tabname}_tree' class='extra-network-tree' style='flex-basis: {extra_networks_tree_view_default_width}px'>
+            {tree_html}
+        </div>
+        <div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards' style='flex-grow: 1;'>
+            {items_html}
+        </div>
+    </div>

html/extra-networks-pane.html

@@ -0,0 +1,81 @@
+<div id='{tabname}_{extra_networks_tabname}_pane' class='extra-network-pane {tree_view_div_default_display_class}'>
+    <div class="extra-network-control" id="{tabname}_{extra_networks_tabname}_controls" style="display:none" >
+        <div class="extra-network-control--search">
+            <input
+                id="{tabname}_{extra_networks_tabname}_extra_search"
+                class="extra-network-control--search-text"
+                type="search"
+                placeholder="Search"
+            >
+        </div>
+
+        <small>Sort: </small>
+        <div 
+            id="{tabname}_{extra_networks_tabname}_extra_sort_path"
+            class="extra-network-control--sort{sort_path_active}"
+            data-sortkey="default"
+            title="Sort by path"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_name"
+            class="extra-network-control--sort{sort_name_active}"
+            data-sortkey="name"
+            title="Sort by name"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_date_created"
+            class="extra-network-control--sort{sort_date_created_active}"
+            data-sortkey="date_created"
+            title="Sort by date created"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_date_modified"
+            class="extra-network-control--sort{sort_date_modified_active}"
+            data-sortkey="date_modified"
+            title="Sort by date modified"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+
+        <small> </small>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_dir"
+            class="extra-network-control--sort-dir"
+            data-sortdir="{data_sortdir}"
+            title="Sort ascending"
+            onclick="extraNetworksControlSortDirOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-dir-icon"></i>
+        </div>
+
+
+        <small> </small>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_tree_view"
+            class="extra-network-control--tree-view {tree_view_btn_extra_class}"
+            title="Enable Tree View"
+            onclick="extraNetworksControlTreeViewOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--tree-view-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_refresh"
+            class="extra-network-control--refresh"
+            title="Refresh page"
+            onclick="extraNetworksControlRefreshOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--refresh-icon"></i>
+        </div>
+    </div>
+    {pane_content}
+</div>

html/extra-networks-tree-button.html

@@ -0,0 +1,23 @@
+<span data-filterable-item-text hidden>{search_terms}</span>
+<div class="tree-list-content {subclass}"
+    type="button"
+    onclick="extraNetworksTreeOnClick(event, '{tabname}', '{extra_networks_tabname}');{onclick_extra}"
+    data-path="{data_path}"
+    data-hash="{data_hash}"
+>
+    <span class='tree-list-item-action tree-list-item-action--leading'>
+        {action_list_item_action_leading}
+    </span>
+    <span class="tree-list-item-visual tree-list-item-visual--leading">
+        {action_list_item_visual_leading}
+    </span>
+    <span class="tree-list-item-label tree-list-item-label--truncate">
+        {action_list_item_label}
+    </span>
+    <span class="tree-list-item-visual tree-list-item-visual--trailing">
+        {action_list_item_visual_trailing}
+    </span>
+    <span class="tree-list-item-action tree-list-item-action--trailing">
+        {action_list_item_action_trailing}
+    </span>
+</div>

html/licenses.html

@@ -4,107 +4,6 @@
     #licenses pre { margin: 1em 0 2em 0;}
 </style>
 
-<h2><a href="https://github.com/sczhou/CodeFormer/blob/master/LICENSE">CodeFormer</a></h2>
-<small>Parts of CodeFormer code had to be copied to be compatible with GFPGAN.</small>
-<pre>
-S-Lab License 1.0
-
-Copyright 2022 S-Lab
-
-Redistribution and use for non-commercial purpose in source and
-binary forms, with or without modification, are permitted provided
-that the following conditions are met:
-
-1. Redistributions of source code must retain the above copyright
-   notice, this list of conditions and the following disclaimer.
-
-2. Redistributions in binary form must reproduce the above copyright
-   notice, this list of conditions and the following disclaimer in
-   the documentation and/or other materials provided with the
-   distribution.
-
-3. Neither the name of the copyright holder nor the names of its
-   contributors may be used to endorse or promote products derived
-   from this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-In the event that redistribution and/or use for commercial purpose in
-source or binary forms, with or without modification is required,
-please contact the contributor(s) of the work.
-</pre>
-
-
-<h2><a href="https://github.com/victorca25/iNNfer/blob/main/LICENSE">ESRGAN</a></h2>
-<small>Code for architecture and reading models copied.</small>
-<pre>
-MIT License
-
-Copyright (c) 2021 victorca25
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
-</pre>
-
-<h2><a href="https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE">Real-ESRGAN</a></h2>
-<small>Some code is copied to support ESRGAN models.</small>
-<pre>
-BSD 3-Clause License
-
-Copyright (c) 2021, Xintao Wang
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-1. Redistributions of source code must retain the above copyright notice, this
-   list of conditions and the following disclaimer.
-
-2. Redistributions in binary form must reproduce the above copyright notice,
-   this list of conditions and the following disclaimer in the documentation
-   and/or other materials provided with the distribution.
-
-3. Neither the name of the copyright holder nor the names of its
-   contributors may be used to endorse or promote products derived from
-   this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
-FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-</pre>
-
 <h2><a href="https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE">InvokeAI</a></h2>
 <small>Some code for compatibility with OSX is taken from lstein's repository.</small>
 <pre>
@@ -183,213 +82,6 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
 </pre>
 
-<h2><a href="https://github.com/JingyunLiang/SwinIR/blob/main/LICENSE">SwinIR</a></h2>
-<small>Code added by contributors, most likely copied from this repository.</small>
-
-<pre>
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [2021] [SwinIR Authors]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
-</pre>
-
 <h2><a href="https://github.com/AminRezaei0x443/memory-efficient-attention/blob/main/LICENSE">Memory Efficient Attention</a></h2>
 <small>The sub-quadratic cross attention optimization uses modified code from the Memory Efficient Attention package that Alex Birch optimized for 3D tensors. This license is updated to reflect that.</small>
 <pre>
@@ -687,4 +379,4 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
-</pre>
+</pre>

javascript/aspectRatioOverlay.js

@@ -50,17 +50,17 @@ function dimensionChange(e, is_width, is_height) {
         var scaledx = targetElement.naturalWidth * viewportscale;
         var scaledy = targetElement.naturalHeight * viewportscale;
 
-        var cleintRectTop = (viewportOffset.top + window.scrollY);
-        var cleintRectLeft = (viewportOffset.left + window.scrollX);
-        var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight / 2);
-        var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth / 2);
+        var clientRectTop = (viewportOffset.top + window.scrollY);
+        var clientRectLeft = (viewportOffset.left + window.scrollX);
+        var clientRectCentreY = clientRectTop + (targetElement.clientHeight / 2);
+        var clientRectCentreX = clientRectLeft + (targetElement.clientWidth / 2);
 
         var arscale = Math.min(scaledx / currentWidth, scaledy / currentHeight);
         var arscaledx = currentWidth * arscale;
         var arscaledy = currentHeight * arscale;
 
-        var arRectTop = cleintRectCentreY - (arscaledy / 2);
-        var arRectLeft = cleintRectCentreX - (arscaledx / 2);
+        var arRectTop = clientRectCentreY - (arscaledy / 2);
+        var arRectLeft = clientRectCentreX - (arscaledx / 2);
         var arRectWidth = arscaledx;
         var arRectHeight = arscaledy;
 

javascript/contextMenus.js

@@ -8,9 +8,6 @@ var contextMenuInit = function() {
     };
 
     function showContextMenu(event, element, menuEntries) {
-        let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft;
-        let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop;
-
         let oldMenu = gradioApp().querySelector('#context-menu');
         if (oldMenu) {
             oldMenu.remove();
@@ -23,10 +20,8 @@ var contextMenuInit = function() {
         contextMenu.style.background = baseStyle.background;
         contextMenu.style.color = baseStyle.color;
         contextMenu.style.fontFamily = baseStyle.fontFamily;
-        contextMenu.style.top = posy + 'px';
-        contextMenu.style.left = posx + 'px';
-
-
+        contextMenu.style.top = event.pageY + 'px';
+        contextMenu.style.left = event.pageX + 'px';
 
         const contextMenuList = document.createElement('ul');
         contextMenuList.className = 'context-menu-items';
@@ -43,21 +38,6 @@ var contextMenuInit = function() {
         });
 
         gradioApp().appendChild(contextMenu);
-
-        let menuWidth = contextMenu.offsetWidth + 4;
-        let menuHeight = contextMenu.offsetHeight + 4;
-
-        let windowWidth = window.innerWidth;
-        let windowHeight = window.innerHeight;
-
-        if ((windowWidth - posx) < menuWidth) {
-            contextMenu.style.left = windowWidth - menuWidth + "px";
-        }
-
-        if ((windowHeight - posy) < menuHeight) {
-            contextMenu.style.top = windowHeight - menuHeight + "px";
-        }
-
     }
 
     function appendContextMenuOption(targetElementSelector, entryName, entryFunction) {
@@ -107,16 +87,23 @@ var contextMenuInit = function() {
                 oldMenu.remove();
             }
         });
-        gradioApp().addEventListener("contextmenu", function(e) {
-            let oldMenu = gradioApp().querySelector('#context-menu');
-            if (oldMenu) {
-                oldMenu.remove();
-            }
-            menuSpecs.forEach(function(v, k) {
-                if (e.composedPath()[0].matches(k)) {
-                    showContextMenu(e, e.composedPath()[0], v);
-                    e.preventDefault();
+        ['contextmenu', 'touchstart'].forEach((eventType) => {
+            gradioApp().addEventListener(eventType, function(e) {
+                let ev = e;
+                if (eventType.startsWith('touch')) {
+                    if (e.touches.length !== 2) return;
+                    ev = e.touches[0];
                 }
+                let oldMenu = gradioApp().querySelector('#context-menu');
+                if (oldMenu) {
+                    oldMenu.remove();
+                }
+                menuSpecs.forEach(function(v, k) {
+                    if (e.composedPath()[0].matches(k)) {
+                        showContextMenu(ev, e.composedPath()[0], v);
+                        e.preventDefault();
+                    }
+                });
             });
         });
         eventListenerApplied = true;

javascript/dragdrop.js

@@ -56,6 +56,15 @@ function eventHasFiles(e) {
     return false;
 }
 
+function isURL(url) {
+    try {
+        const _ = new URL(url);
+        return true;
+    } catch {
+        return false;
+    }
+}
+
 function dragDropTargetIsPrompt(target) {
     if (target?.placeholder && target?.placeholder.indexOf("Prompt") >= 0) return true;
     if (target?.parentNode?.parentNode?.className?.indexOf("prompt") > 0) return true;
@@ -74,22 +83,39 @@ window.document.addEventListener('dragover', e => {
     e.dataTransfer.dropEffect = 'copy';
 });
 
-window.document.addEventListener('drop', e => {
+window.document.addEventListener('drop', async e => {
     const target = e.composedPath()[0];
-    if (!eventHasFiles(e)) return;
+    const url = e.dataTransfer.getData('text/uri-list') || e.dataTransfer.getData('text/plain');
+    if (!eventHasFiles(e) && !isURL(url)) return;
 
     if (dragDropTargetIsPrompt(target)) {
         e.stopPropagation();
         e.preventDefault();
 
-        let prompt_target = get_tab_index('tabs') == 1 ? "img2img_prompt_image" : "txt2img_prompt_image";
+        const isImg2img = get_tab_index('tabs') == 1;
+        let prompt_image_target = isImg2img ? "img2img_prompt_image" : "txt2img_prompt_image";
 
-        const imgParent = gradioApp().getElementById(prompt_target);
+        const imgParent = gradioApp().getElementById(prompt_image_target);
         const files = e.dataTransfer.files;
         const fileInput = imgParent.querySelector('input[type="file"]');
-        if (fileInput) {
+        if (eventHasFiles(e) && fileInput) {
             fileInput.files = files;
             fileInput.dispatchEvent(new Event('change'));
+        } else if (url) {
+            try {
+                const request = await fetch(url);
+                if (!request.ok) {
+                    console.error('Error fetching URL:', url, request.status);
+                    return;
+                }
+                const data = new DataTransfer();
+                data.items.add(new File([await request.blob()], 'image.png'));
+                fileInput.files = data.files;
+                fileInput.dispatchEvent(new Event('change'));
+            } catch (error) {
+                console.error('Error fetching URL:', url, error);
+                return;
+            }
         }
     }
 

javascript/edit-attention.js

@@ -64,6 +64,14 @@ function keyupEditAttention(event) {
             selectionEnd++;
         }
 
+        // deselect surrounding whitespace
+        while (text[selectionStart] == " " && selectionStart < selectionEnd) {
+            selectionStart++;
+        }
+        while (text[selectionEnd - 1] == " " && selectionEnd > selectionStart) {
+            selectionEnd--;
+        }
+
         target.setSelectionRange(selectionStart, selectionEnd);
         return true;
     }

javascript/extensions.js

@@ -2,8 +2,11 @@
 function extensions_apply(_disabled_list, _update_list, disable_all) {
     var disable = [];
     var update = [];
-
-    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
+    const extensions_input = gradioApp().querySelectorAll('#extensions input[type="checkbox"]');
+    if (extensions_input.length == 0) {
+        throw Error("Extensions page not yet loaded.");
+    }
+    extensions_input.forEach(function(x) {
         if (x.name.startsWith("enable_") && !x.checked) {
             disable.push(x.name.substring(7));
         }

javascript/extraNetworks.js

@@ -16,99 +16,116 @@ function toggleCss(key, css, enable) {
 }
 
 function setupExtraNetworksForTab(tabname) {
-    gradioApp().querySelector('#' + tabname + '_extra_tabs').classList.add('extra-networks');
+    function registerPrompt(tabname, id) {
+        var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
 
-    var tabs = gradioApp().querySelector('#' + tabname + '_extra_tabs > div');
-    var searchDiv = gradioApp().getElementById(tabname + '_extra_search');
-    var search = searchDiv.querySelector('textarea');
-    var sort = gradioApp().getElementById(tabname + '_extra_sort');
-    var sortOrder = gradioApp().getElementById(tabname + '_extra_sortorder');
-    var refresh = gradioApp().getElementById(tabname + '_extra_refresh');
-    var showDirsDiv = gradioApp().getElementById(tabname + '_extra_show_dirs');
-    var showDirs = gradioApp().querySelector('#' + tabname + '_extra_show_dirs input');
-    var promptContainer = gradioApp().querySelector('.prompt-container-compact#' + tabname + '_prompt_container');
-    var negativePrompt = gradioApp().querySelector('#' + tabname + '_neg_prompt');
+        if (!activePromptTextarea[tabname]) {
+            activePromptTextarea[tabname] = textarea;
+        }
 
-    tabs.appendChild(searchDiv);
-    tabs.appendChild(sort);
-    tabs.appendChild(sortOrder);
-    tabs.appendChild(refresh);
-    tabs.appendChild(showDirsDiv);
+        textarea.addEventListener("focus", function() {
+            activePromptTextarea[tabname] = textarea;
+        });
+    }
 
-    var applyFilter = function() {
-        var searchTerm = search.value.toLowerCase();
+    var tabnav = gradioApp().querySelector('#' + tabname + '_extra_tabs > div.tab-nav');
+    var controlsDiv = document.createElement('DIV');
+    controlsDiv.classList.add('extra-networks-controls-div');
+    tabnav.appendChild(controlsDiv);
+    tabnav.insertBefore(controlsDiv, null);
 
-        gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
-            var searchOnly = elem.querySelector('.search_only');
-            var text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase();
+    var this_tab = gradioApp().querySelector('#' + tabname + '_extra_tabs');
+    this_tab.querySelectorAll(":scope > [id^='" + tabname + "_']").forEach(function(elem) {
+        // tabname_full = {tabname}_{extra_networks_tabname}
+        var tabname_full = elem.id;
+        var search = gradioApp().querySelector("#" + tabname_full + "_extra_search");
+        var sort_dir = gradioApp().querySelector("#" + tabname_full + "_extra_sort_dir");
+        var refresh = gradioApp().querySelector("#" + tabname_full + "_extra_refresh");
+        var currentSort = '';
 
-            var visible = text.indexOf(searchTerm) != -1;
+        // If any of the buttons above don't exist, we want to skip this iteration of the loop.
+        if (!search || !sort_dir || !refresh) {
+            return; // `return` is equivalent of `continue` but for forEach loops.
+        }
 
-            if (searchOnly && searchTerm.length < 4) {
-                visible = false;
+        var applyFilter = function(force) {
+            var searchTerm = search.value.toLowerCase();
+            gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
+                var searchOnly = elem.querySelector('.search_only');
+                var text = Array.prototype.map.call(elem.querySelectorAll('.search_terms, .description'), function(t) {
+                    return t.textContent.toLowerCase();
+                }).join(" ");
+
+                var visible = text.indexOf(searchTerm) != -1;
+                if (searchOnly && searchTerm.length < 4) {
+                    visible = false;
+                }
+                if (visible) {
+                    elem.classList.remove("hidden");
+                } else {
+                    elem.classList.add("hidden");
+                }
+            });
+
+            applySort(force);
+        };
+
+        var applySort = function(force) {
+            var cards = gradioApp().querySelectorAll('#' + tabname_full + ' div.card');
+            var parent = gradioApp().querySelector('#' + tabname_full + "_cards");
+            var reverse = sort_dir.dataset.sortdir == "Descending";
+            var activeSearchElem = gradioApp().querySelector('#' + tabname_full + "_controls .extra-network-control--sort.extra-network-control--enabled");
+            var sortKey = activeSearchElem ? activeSearchElem.dataset.sortkey : "default";
+            var sortKeyDataField = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1);
+            var sortKeyStore = sortKey + "-" + sort_dir.dataset.sortdir + "-" + cards.length;
+
+            if (sortKeyStore == currentSort && !force) {
+                return;
+            }
+            currentSort = sortKeyStore;
+
+            var sortedCards = Array.from(cards);
+            sortedCards.sort(function(cardA, cardB) {
+                var a = cardA.dataset[sortKeyDataField];
+                var b = cardB.dataset[sortKeyDataField];
+                if (!isNaN(a) && !isNaN(b)) {
+                    return parseInt(a) - parseInt(b);
+                }
+
+                return (a < b ? -1 : (a > b ? 1 : 0));
+            });
+
+            if (reverse) {
+                sortedCards.reverse();
             }
 
-            elem.style.display = visible ? "" : "none";
-        });
+            parent.innerHTML = '';
 
+            var frag = document.createDocumentFragment();
+            sortedCards.forEach(function(card) {
+                frag.appendChild(card);
+            });
+            parent.appendChild(frag);
+        };
+
+        search.addEventListener("input", function() {
+            applyFilter();
+        });
         applySort();
-    };
+        applyFilter();
+        extraNetworksApplySort[tabname_full] = applySort;
+        extraNetworksApplyFilter[tabname_full] = applyFilter;
 
-    var applySort = function() {
-        var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card');
+        var controls = gradioApp().querySelector("#" + tabname_full + "_controls");
+        controlsDiv.insertBefore(controls, null);
 
-        var reverse = sortOrder.classList.contains("sortReverse");
-        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim() || "name";
-        sortKey = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1);
-        var sortKeyStore = sortKey + "-" + (reverse ? "Descending" : "Ascending") + "-" + cards.length;
-
-        if (sortKeyStore == sort.dataset.sortkey) {
-            return;
+        if (elem.style.display != "none") {
+            extraNetworksShowControlsForPage(tabname, tabname_full);
         }
-        sort.dataset.sortkey = sortKeyStore;
-
-        cards.forEach(function(card) {
-            card.originalParentElement = card.parentElement;
-        });
-        var sortedCards = Array.from(cards);
-        sortedCards.sort(function(cardA, cardB) {
-            var a = cardA.dataset[sortKey];
-            var b = cardB.dataset[sortKey];
-            if (!isNaN(a) && !isNaN(b)) {
-                return parseInt(a) - parseInt(b);
-            }
-
-            return (a < b ? -1 : (a > b ? 1 : 0));
-        });
-        if (reverse) {
-            sortedCards.reverse();
-        }
-        cards.forEach(function(card) {
-            card.remove();
-        });
-        sortedCards.forEach(function(card) {
-            card.originalParentElement.appendChild(card);
-        });
-    };
-
-    search.addEventListener("input", applyFilter);
-    sortOrder.addEventListener("click", function() {
-        sortOrder.classList.toggle("sortReverse");
-        applySort();
     });
-    applyFilter();
 
-    extraNetworksApplySort[tabname] = applySort;
-    extraNetworksApplyFilter[tabname] = applyFilter;
-
-    var showDirsUpdate = function() {
-        var css = '#' + tabname + '_extra_tabs .extra-network-subdirs { display: none; }';
-        toggleCss(tabname + '_extra_show_dirs_style', css, !showDirs.checked);
-        localSet('extra-networks-show-dirs', showDirs.checked ? 1 : 0);
-    };
-    showDirs.checked = localGet('extra-networks-show-dirs', 1) == 1;
-    showDirs.addEventListener("change", showDirsUpdate);
-    showDirsUpdate();
+    registerPrompt(tabname, tabname + "_prompt");
+    registerPrompt(tabname, tabname + "_neg_prompt");
 }
 
 function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt) {
@@ -137,21 +154,42 @@ function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePromp
 }
 
 
-function extraNetworksUrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate)
-    extraNetworksMovePromptToTab(tabname, '', false, false);
+function extraNetworksShowControlsForPage(tabname, tabname_full) {
+    gradioApp().querySelectorAll('#' + tabname + '_extra_tabs .extra-networks-controls-div > div').forEach(function(elem) {
+        var targetId = tabname_full + "_controls";
+        elem.style.display = elem.id == targetId ? "" : "none";
+    });
 }
 
-function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt) { // called from python when user selects an extra networks tab
+
+function extraNetworksUnrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate)
+    extraNetworksMovePromptToTab(tabname, '', false, false);
+
+    extraNetworksShowControlsForPage(tabname, null);
+}
+
+function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt, tabname_full) { // called from python when user selects an extra networks tab
     extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt);
 
+    extraNetworksShowControlsForPage(tabname, tabname_full);
 }
 
-function applyExtraNetworkFilter(tabname) {
-    setTimeout(extraNetworksApplyFilter[tabname], 1);
+function applyExtraNetworkFilter(tabname_full) {
+    var doFilter = function() {
+        var applyFunction = extraNetworksApplyFilter[tabname_full];
+
+        if (applyFunction) {
+            applyFunction(true);
+        }
+    };
+    setTimeout(doFilter, 1);
 }
 
-function applyExtraNetworkSort(tabname) {
-    setTimeout(extraNetworksApplySort[tabname], 1);
+function applyExtraNetworkSort(tabname_full) {
+    var doSort = function() {
+        extraNetworksApplySort[tabname_full](true);
+    };
+    setTimeout(doSort, 1);
 }
 
 var extraNetworksApplyFilter = {};
@@ -161,41 +199,24 @@ var activePromptTextarea = {};
 function setupExtraNetworks() {
     setupExtraNetworksForTab('txt2img');
     setupExtraNetworksForTab('img2img');
-
-    function registerPrompt(tabname, id) {
-        var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
-
-        if (!activePromptTextarea[tabname]) {
-            activePromptTextarea[tabname] = textarea;
-        }
-
-        textarea.addEventListener("focus", function() {
-            activePromptTextarea[tabname] = textarea;
-        });
-    }
-
-    registerPrompt('txt2img', 'txt2img_prompt');
-    registerPrompt('txt2img', 'txt2img_neg_prompt');
-    registerPrompt('img2img', 'img2img_prompt');
-    registerPrompt('img2img', 'img2img_neg_prompt');
 }
 
-onUiLoaded(setupExtraNetworks);
-
 var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
 var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g;
 
-function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
-    var m = text.match(re_extranet);
+var re_extranet_neg = /\(([^:^>]+:[\d.]+)\)/;
+var re_extranet_g_neg = /\(([^:^>]+:[\d.]+)\)/g;
+function tryToRemoveExtraNetworkFromPrompt(textarea, text, isNeg) {
+    var m = text.match(isNeg ? re_extranet_neg : re_extranet);
     var replaced = false;
     var newTextareaText;
+    var extraTextBeforeNet = opts.extra_networks_add_text_separator;
     if (m) {
-        var extraTextBeforeNet = opts.extra_networks_add_text_separator;
         var extraTextAfterNet = m[2];
         var partToSearch = m[1];
         var foundAtPosition = -1;
-        newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found, net, pos) {
-            m = found.match(re_extranet);
+        newTextareaText = textarea.value.replaceAll(isNeg ? re_extranet_g_neg : re_extranet_g, function(found, net, pos) {
+            m = found.match(isNeg ? re_extranet_neg : re_extranet);
             if (m[1] == partToSearch) {
                 replaced = true;
                 foundAtPosition = pos;
@@ -203,9 +224,8 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
             }
             return found;
         });
-
         if (foundAtPosition >= 0) {
-            if (newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
+            if (extraTextAfterNet && newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
                 newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length);
             }
             if (newTextareaText.substr(foundAtPosition - extraTextBeforeNet.length, extraTextBeforeNet.length) == extraTextBeforeNet) {
@@ -213,13 +233,8 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
             }
         }
     } else {
-        newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found) {
-            if (found == text) {
-                replaced = true;
-                return "";
-            }
-            return found;
-        });
+        newTextareaText = textarea.value.replaceAll(new RegExp(`((?:${extraTextBeforeNet})?${text})`, "g"), "");
+        replaced = (newTextareaText != textarea.value);
     }
 
     if (replaced) {
@@ -230,14 +245,22 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
     return false;
 }
 
-function cardClicked(tabname, textToAdd, allowNegativePrompt) {
-    var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
-
-    if (!tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)) {
-        textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd;
+function updatePromptArea(text, textArea, isNeg) {
+    if (!tryToRemoveExtraNetworkFromPrompt(textArea, text, isNeg)) {
+        textArea.value = textArea.value + opts.extra_networks_add_text_separator + text;
     }
 
-    updateInput(textarea);
+    updateInput(textArea);
+}
+
+function cardClicked(tabname, textToAdd, textToAddNegative, allowNegativePrompt) {
+    if (textToAddNegative.length > 0) {
+        updatePromptArea(textToAdd, gradioApp().querySelector("#" + tabname + "_prompt > label > textarea"));
+        updatePromptArea(textToAddNegative, gradioApp().querySelector("#" + tabname + "_neg_prompt > label > textarea"), true);
+    } else {
+        var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
+        updatePromptArea(textToAdd, textarea);
+    }
 }
 
 function saveCardPreview(event, tabname, filename) {
@@ -253,8 +276,8 @@ function saveCardPreview(event, tabname, filename) {
     event.preventDefault();
 }
 
-function extraNetworksSearchButton(tabs_id, event) {
-    var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > label > textarea');
+function extraNetworksSearchButton(tabname, extra_networks_tabname, event) {
+    var searchTextarea = gradioApp().querySelector("#" + tabname + "_" + extra_networks_tabname + "_extra_search");
     var button = event.target;
     var text = button.classList.contains("search-all") ? "" : button.textContent.trim();
 
@@ -262,6 +285,187 @@ function extraNetworksSearchButton(tabs_id, event) {
     updateInput(searchTextarea);
 }
 
+function extraNetworksTreeProcessFileClick(event, btn, tabname, extra_networks_tabname) {
+    /**
+     * Processes `onclick` events when user clicks on files in tree.
+     *
+     * @param event                     The generated event.
+     * @param btn                       The clicked `tree-list-item` button.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    // NOTE: Currently unused.
+    return;
+}
+
+function extraNetworksTreeProcessDirectoryClick(event, btn, tabname, extra_networks_tabname) {
+    /**
+     * Processes `onclick` events when user clicks on directories in tree.
+     *
+     * Here is how the tree reacts to clicks for various states:
+     * unselected unopened directory: Directory is selected and expanded.
+     * unselected opened directory: Directory is selected.
+     * selected opened directory: Directory is collapsed and deselected.
+     * chevron is clicked: Directory is expanded or collapsed. Selected state unchanged.
+     *
+     * @param event                     The generated event.
+     * @param btn                       The clicked `tree-list-item` button.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var ul = btn.nextElementSibling;
+    // This is the actual target that the user clicked on within the target button.
+    // We use this to detect if the chevron was clicked.
+    var true_targ = event.target;
+
+    function _expand_or_collapse(_ul, _btn) {
+        // Expands <ul> if it is collapsed, collapses otherwise. Updates button attributes.
+        if (_ul.hasAttribute("hidden")) {
+            _ul.removeAttribute("hidden");
+            _btn.dataset.expanded = "";
+        } else {
+            _ul.setAttribute("hidden", "");
+            delete _btn.dataset.expanded;
+        }
+    }
+
+    function _remove_selected_from_all() {
+        // Removes the `selected` attribute from all buttons.
+        var sels = document.querySelectorAll("div.tree-list-content");
+        [...sels].forEach(el => {
+            delete el.dataset.selected;
+        });
+    }
+
+    function _select_button(_btn) {
+        // Removes `data-selected` attribute from all buttons then adds to passed button.
+        _remove_selected_from_all();
+        _btn.dataset.selected = "";
+    }
+
+    function _update_search(_tabname, _extra_networks_tabname, _search_text) {
+        // Update search input with select button's path.
+        var search_input_elem = gradioApp().querySelector("#" + tabname + "_" + extra_networks_tabname + "_extra_search");
+        search_input_elem.value = _search_text;
+        updateInput(search_input_elem);
+    }
+
+
+    // If user clicks on the chevron, then we do not select the folder.
+    if (true_targ.matches(".tree-list-item-action--leading, .tree-list-item-action-chevron")) {
+        _expand_or_collapse(ul, btn);
+    } else {
+        // User clicked anywhere else on the button.
+        if ("selected" in btn.dataset && !(ul.hasAttribute("hidden"))) {
+            // If folder is select and open, collapse and deselect button.
+            _expand_or_collapse(ul, btn);
+            delete btn.dataset.selected;
+            _update_search(tabname, extra_networks_tabname, "");
+        } else if (!(!("selected" in btn.dataset) && !(ul.hasAttribute("hidden")))) {
+            // If folder is open and not selected, then we don't collapse; just select.
+            // NOTE: Double inversion sucks but it is the clearest way to show the branching here.
+            _expand_or_collapse(ul, btn);
+            _select_button(btn, tabname, extra_networks_tabname);
+            _update_search(tabname, extra_networks_tabname, btn.dataset.path);
+        } else {
+            // All other cases, just select the button.
+            _select_button(btn, tabname, extra_networks_tabname);
+            _update_search(tabname, extra_networks_tabname, btn.dataset.path);
+        }
+    }
+}
+
+function extraNetworksTreeOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for buttons within an `extra-network-tree .tree-list--tree`.
+     *
+     * Determines whether the clicked button in the tree is for a file entry or a directory
+     * then calls the appropriate function.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var btn = event.currentTarget;
+    var par = btn.parentElement;
+    if (par.dataset.treeEntryType === "file") {
+        extraNetworksTreeProcessFileClick(event, btn, tabname, extra_networks_tabname);
+    } else {
+        extraNetworksTreeProcessDirectoryClick(event, btn, tabname, extra_networks_tabname);
+    }
+}
+
+function extraNetworksControlSortOnClick(event, tabname, extra_networks_tabname) {
+    /** Handles `onclick` events for Sort Mode buttons. */
+
+    var self = event.currentTarget;
+    var parent = event.currentTarget.parentElement;
+
+    parent.querySelectorAll('.extra-network-control--sort').forEach(function(x) {
+        x.classList.remove('extra-network-control--enabled');
+    });
+
+    self.classList.add('extra-network-control--enabled');
+
+    applyExtraNetworkSort(tabname + "_" + extra_networks_tabname);
+}
+
+function extraNetworksControlSortDirOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for the Sort Direction button.
+     *
+     * Modifies the data attributes of the Sort Direction button to cycle between
+     * ascending and descending sort directions.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    if (event.currentTarget.dataset.sortdir == "Ascending") {
+        event.currentTarget.dataset.sortdir = "Descending";
+        event.currentTarget.setAttribute("title", "Sort descending");
+    } else {
+        event.currentTarget.dataset.sortdir = "Ascending";
+        event.currentTarget.setAttribute("title", "Sort ascending");
+    }
+    applyExtraNetworkSort(tabname + "_" + extra_networks_tabname);
+}
+
+function extraNetworksControlTreeViewOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for the Tree View button.
+     *
+     * Toggles the tree view in the extra networks pane.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var button = event.currentTarget;
+    button.classList.toggle("extra-network-control--enabled");
+    var show = !button.classList.contains("extra-network-control--enabled");
+
+    var pane = gradioApp().getElementById(tabname + "_" + extra_networks_tabname + "_pane");
+    pane.classList.toggle("extra-network-dirs-hidden", show);
+}
+
+function extraNetworksControlRefreshOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for the Refresh Page button.
+     *
+     * In order to actually call the python functions in `ui_extra_networks.py`
+     * to refresh the page, we created an empty gradio button in that file with an
+     * event handler that refreshes the page. So what this function here does
+     * is it manually raises a `click` event on that button.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var btn_refresh_internal = gradioApp().getElementById(tabname + "_" + extra_networks_tabname + "_extra_refresh_internal");
+    btn_refresh_internal.dispatchEvent(new Event("click"));
+}
+
 var globalPopup = null;
 var globalPopupInner = null;
 
@@ -303,12 +507,76 @@ function popupId(id) {
     popup(storedPopupIds[id]);
 }
 
+function extraNetworksFlattenMetadata(obj) {
+    const result = {};
+
+    // Convert any stringified JSON objects to actual objects
+    for (const key of Object.keys(obj)) {
+        if (typeof obj[key] === 'string') {
+            try {
+                const parsed = JSON.parse(obj[key]);
+                if (parsed && typeof parsed === 'object') {
+                    obj[key] = parsed;
+                }
+            } catch (error) {
+                continue;
+            }
+        }
+    }
+
+    // Flatten the object
+    for (const key of Object.keys(obj)) {
+        if (typeof obj[key] === 'object' && obj[key] !== null) {
+            const nested = extraNetworksFlattenMetadata(obj[key]);
+            for (const nestedKey of Object.keys(nested)) {
+                result[`${key}/${nestedKey}`] = nested[nestedKey];
+            }
+        } else {
+            result[key] = obj[key];
+        }
+    }
+
+    // Special case for handling modelspec keys
+    for (const key of Object.keys(result)) {
+        if (key.startsWith("modelspec.")) {
+            result[key.replaceAll(".", "/")] = result[key];
+            delete result[key];
+        }
+    }
+
+    // Add empty keys to designate hierarchy
+    for (const key of Object.keys(result)) {
+        const parts = key.split("/");
+        for (let i = 1; i < parts.length; i++) {
+            const parent = parts.slice(0, i).join("/");
+            if (!result[parent]) {
+                result[parent] = "";
+            }
+        }
+    }
+
+    return result;
+}
+
 function extraNetworksShowMetadata(text) {
+    try {
+        let parsed = JSON.parse(text);
+        if (parsed && typeof parsed === 'object') {
+            parsed = extraNetworksFlattenMetadata(parsed);
+            const table = createVisualizationTable(parsed, 0);
+            popup(table);
+            return;
+        }
+    } catch (error) {
+        console.error(error);
+    }
+
     var elem = document.createElement('pre');
     elem.classList.add('popup-metadata');
     elem.textContent = text;
 
     popup(elem);
+    return;
 }
 
 function requestGet(url, data, handler, errorHandler) {
@@ -337,11 +605,18 @@ function requestGet(url, data, handler, errorHandler) {
     xhr.send(js);
 }
 
-function extraNetworksRequestMetadata(event, extraPage, cardName) {
+function extraNetworksCopyCardPath(event) {
+    navigator.clipboard.writeText(event.target.getAttribute("data-clipboard-text"));
+    event.stopPropagation();
+}
+
+function extraNetworksRequestMetadata(event, extraPage) {
     var showError = function() {
         extraNetworksShowMetadata("there was an error getting metadata");
     };
 
+    var cardName = event.target.parentElement.parentElement.getAttribute("data-name");
+
     requestGet("./sd_extra_networks/metadata", {page: extraPage, item: cardName}, function(data) {
         if (data && data.metadata) {
             extraNetworksShowMetadata(data.metadata);
@@ -355,7 +630,7 @@ function extraNetworksRequestMetadata(event, extraPage, cardName) {
 
 var extraPageUserMetadataEditors = {};
 
-function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) {
+function extraNetworksEditUserMetadata(event, tabname, extraPage) {
     var id = tabname + '_' + extraPage + '_edit_user_metadata';
 
     var editor = extraPageUserMetadataEditors[id];
@@ -367,6 +642,7 @@ function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) {
         extraPageUserMetadataEditors[id] = editor;
     }
 
+    var cardName = event.target.parentElement.parentElement.getAttribute("data-name");
     editor.nameTextarea.value = cardName;
     updateInput(editor.nameTextarea);
 
@@ -398,3 +674,39 @@ window.addEventListener("keydown", function(event) {
         closePopup();
     }
 });
+
+/**
+ * Setup custom loading for this script.
+ * We need to wait for all of our HTML to be generated in the extra networks tabs
+ * before we can actually run the `setupExtraNetworks` function.
+ * The `onUiLoaded` function actually runs before all of our extra network tabs are
+ * finished generating. Thus we needed this new method.
+ *
+ */
+
+var uiAfterScriptsCallbacks = [];
+var uiAfterScriptsTimeout = null;
+var executedAfterScripts = false;
+
+function scheduleAfterScriptsCallbacks() {
+    clearTimeout(uiAfterScriptsTimeout);
+    uiAfterScriptsTimeout = setTimeout(function() {
+        executeCallbacks(uiAfterScriptsCallbacks);
+    }, 200);
+}
+
+onUiLoaded(function() {
+    var mutationObserver = new MutationObserver(function(m) {
+        let existingSearchfields = gradioApp().querySelectorAll("[id$='_extra_search']").length;
+        let neededSearchfields = gradioApp().querySelectorAll("[id$='_extra_tabs'] > .tab-nav > button").length - 2;
+
+        if (!executedAfterScripts && existingSearchfields >= neededSearchfields) {
+            mutationObserver.disconnect();
+            executedAfterScripts = true;
+            scheduleAfterScriptsCallbacks();
+        }
+    });
+    mutationObserver.observe(gradioApp(), {childList: true, subtree: true});
+});
+
+uiAfterScriptsCallbacks.push(setupExtraNetworks);

javascript/imageviewer.js

@@ -6,6 +6,8 @@ function closeModal() {
 function showModal(event) {
     const source = event.target || event.srcElement;
     const modalImage = gradioApp().getElementById("modalImage");
+    const modalToggleLivePreviewBtn = gradioApp().getElementById("modal_toggle_live_preview");
+    modalToggleLivePreviewBtn.innerHTML = opts.js_live_preview_in_modal_lightbox ? "🗇" : "🗆";
     const lb = gradioApp().getElementById("lightboxModal");
     modalImage.src = source.src;
     if (modalImage.style.display === 'none') {
@@ -34,7 +36,7 @@ function updateOnBackgroundChange() {
     if (modalImage && modalImage.offsetParent) {
         let currentButton = selected_gallery_button();
         let preview = gradioApp().querySelectorAll('.livePreview > img');
-        if (preview.length > 0) {
+        if (opts.js_live_preview_in_modal_lightbox && preview.length > 0) {
             // show preview image if available
             modalImage.src = preview[preview.length - 1].src;
         } else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
@@ -51,14 +53,7 @@ function modalImageSwitch(offset) {
     var galleryButtons = all_gallery_buttons();
 
     if (galleryButtons.length > 1) {
-        var currentButton = selected_gallery_button();
-
-        var result = -1;
-        galleryButtons.forEach(function(v, i) {
-            if (v == currentButton) {
-                result = i;
-            }
-        });
+        var result = selected_gallery_index();
 
         if (result != -1) {
             var nextButton = galleryButtons[negmod((result + offset), galleryButtons.length)];
@@ -131,19 +126,15 @@ function setupImageForLightbox(e) {
     e.style.cursor = 'pointer';
     e.style.userSelect = 'none';
 
-    var isFirefox = navigator.userAgent.toLowerCase().indexOf('firefox') > -1;
-
-    // For Firefox, listening on click first switched to next image then shows the lightbox.
-    // If you know how to fix this without switching to mousedown event, please.
-    // For other browsers the event is click to make it possiblr to drag picture.
-    var event = isFirefox ? 'mousedown' : 'click';
-
-    e.addEventListener(event, function(evt) {
+    e.addEventListener('mousedown', function(evt) {
         if (evt.button == 1) {
             open(evt.target.src);
             evt.preventDefault();
             return;
         }
+    }, true);
+
+    e.addEventListener('click', function(evt) {
         if (!opts.js_modal_lightbox || evt.button != 0) return;
 
         modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed);
@@ -163,6 +154,13 @@ function modalZoomToggle(event) {
     event.stopPropagation();
 }
 
+function modalLivePreviewToggle(event) {
+    const modalToggleLivePreview = gradioApp().getElementById("modal_toggle_live_preview");
+    opts.js_live_preview_in_modal_lightbox = !opts.js_live_preview_in_modal_lightbox;
+    modalToggleLivePreview.innerHTML = opts.js_live_preview_in_modal_lightbox ? "🗇" : "🗆";
+    event.stopPropagation();
+}
+
 function modalTileImageToggle(event) {
     const modalImage = gradioApp().getElementById("modalImage");
     const modal = gradioApp().getElementById("lightboxModal");
@@ -220,6 +218,14 @@ document.addEventListener("DOMContentLoaded", function() {
     modalSave.title = "Save Image(s)";
     modalControls.appendChild(modalSave);
 
+    const modalToggleLivePreview = document.createElement('span');
+    modalToggleLivePreview.className = 'modalToggleLivePreview cursor';
+    modalToggleLivePreview.id = "modal_toggle_live_preview";
+    modalToggleLivePreview.innerHTML = "🗆";
+    modalToggleLivePreview.onclick = modalLivePreviewToggle;
+    modalToggleLivePreview.title = "Toggle live preview";
+    modalControls.appendChild(modalToggleLivePreview);
+
     const modalClose = document.createElement('span');
     modalClose.className = 'modalClose cursor';
     modalClose.innerHTML = '×';

javascript/profilerVisualization.js

@@ -33,120 +33,141 @@ function createRow(table, cellName, items) {
     return res;
 }
 
-function showProfile(path, cutoff = 0.05) {
-    requestGet(path, {}, function(data) {
-        var table = document.createElement('table');
-        table.className = 'popup-table';
+function createVisualizationTable(data, cutoff = 0, sort = "") {
+    var table = document.createElement('table');
+    table.className = 'popup-table';
 
-        data.records['total'] = data.total;
-        var keys = Object.keys(data.records).sort(function(a, b) {
-            return data.records[b] - data.records[a];
+    var keys = Object.keys(data);
+    if (sort === "number") {
+        keys = keys.sort(function(a, b) {
+            return data[b] - data[a];
         });
-        var items = keys.map(function(x) {
-            return {key: x, parts: x.split('/'), time: data.records[x]};
+    } else {
+        keys = keys.sort();
+    }
+    var items = keys.map(function(x) {
+        return {key: x, parts: x.split('/'), value: data[x]};
+    });
+    var maxLength = items.reduce(function(a, b) {
+        return Math.max(a, b.parts.length);
+    }, 0);
+
+    var cols = createRow(
+        table,
+        'th',
+        [
+            cutoff === 0 ? 'key' : 'record',
+            cutoff === 0 ? 'value' : 'seconds'
+        ]
+    );
+    cols[0].colSpan = maxLength;
+
+    function arraysEqual(a, b) {
+        return !(a < b || b < a);
+    }
+
+    var addLevel = function(level, parent, hide) {
+        var matching = items.filter(function(x) {
+            return x.parts[level] && !x.parts[level + 1] && arraysEqual(x.parts.slice(0, level), parent);
         });
-        var maxLength = items.reduce(function(a, b) {
-            return Math.max(a, b.parts.length);
-        }, 0);
-
-        var cols = createRow(table, 'th', ['record', 'seconds']);
-        cols[0].colSpan = maxLength;
-
-        function arraysEqual(a, b) {
-            return !(a < b || b < a);
+        if (sort === "number") {
+            matching = matching.sort(function(a, b) {
+                return b.value - a.value;
+            });
+        } else {
+            matching = matching.sort();
         }
+        var othersTime = 0;
+        var othersList = [];
+        var othersRows = [];
+        var childrenRows = [];
+        matching.forEach(function(x) {
+            var visible = (cutoff === 0 && !hide) || (x.value >= cutoff && !hide);
 
-        var addLevel = function(level, parent, hide) {
-            var matching = items.filter(function(x) {
-                return x.parts[level] && !x.parts[level + 1] && arraysEqual(x.parts.slice(0, level), parent);
-            });
-            var sorted = matching.sort(function(a, b) {
-                return b.time - a.time;
-            });
-            var othersTime = 0;
-            var othersList = [];
-            var othersRows = [];
-            var childrenRows = [];
-            sorted.forEach(function(x) {
-                var visible = x.time >= cutoff && !hide;
+            var cells = [];
+            for (var i = 0; i < maxLength; i++) {
+                cells.push(x.parts[i]);
+            }
+            cells.push(cutoff === 0 ? x.value : x.value.toFixed(3));
+            var cols = createRow(table, 'td', cells);
+            for (i = 0; i < level; i++) {
+                cols[i].className = 'muted';
+            }
 
-                var cells = [];
-                for (var i = 0; i < maxLength; i++) {
-                    cells.push(x.parts[i]);
-                }
-                cells.push(x.time.toFixed(3));
-                var cols = createRow(table, 'td', cells);
-                for (i = 0; i < level; i++) {
-                    cols[i].className = 'muted';
-                }
+            var tr = cols[0].parentNode;
+            if (!visible) {
+                tr.classList.add("hidden");
+            }
 
-                var tr = cols[0].parentNode;
-                if (!visible) {
-                    tr.classList.add("hidden");
-                }
-
-                if (x.time >= cutoff) {
-                    childrenRows.push(tr);
-                } else {
-                    othersTime += x.time;
-                    othersList.push(x.parts[level]);
-                    othersRows.push(tr);
-                }
-
-                var children = addLevel(level + 1, parent.concat([x.parts[level]]), true);
-                if (children.length > 0) {
-                    var cell = cols[level];
-                    var onclick = function() {
-                        cell.classList.remove("link");
-                        cell.removeEventListener("click", onclick);
-                        children.forEach(function(x) {
-                            x.classList.remove("hidden");
-                        });
-                    };
-                    cell.classList.add("link");
-                    cell.addEventListener("click", onclick);
-                }
-            });
-
-            if (othersTime > 0) {
-                var cells = [];
-                for (var i = 0; i < maxLength; i++) {
-                    cells.push(parent[i]);
-                }
-                cells.push(othersTime.toFixed(3));
-                cells[level] = 'others';
-                var cols = createRow(table, 'td', cells);
-                for (i = 0; i < level; i++) {
-                    cols[i].className = 'muted';
-                }
+            if (cutoff === 0 || x.value >= cutoff) {
+                childrenRows.push(tr);
+            } else {
+                othersTime += x.value;
+                othersList.push(x.parts[level]);
+                othersRows.push(tr);
+            }
 
+            var children = addLevel(level + 1, parent.concat([x.parts[level]]), true);
+            if (children.length > 0) {
                 var cell = cols[level];
-                var tr = cell.parentNode;
                 var onclick = function() {
-                    tr.classList.add("hidden");
                     cell.classList.remove("link");
                     cell.removeEventListener("click", onclick);
-                    othersRows.forEach(function(x) {
+                    children.forEach(function(x) {
                         x.classList.remove("hidden");
                     });
                 };
-
-                cell.title = othersList.join(", ");
                 cell.classList.add("link");
                 cell.addEventListener("click", onclick);
+            }
+        });
 
-                if (hide) {
-                    tr.classList.add("hidden");
-                }
-
-                childrenRows.push(tr);
+        if (othersTime > 0) {
+            var cells = [];
+            for (var i = 0; i < maxLength; i++) {
+                cells.push(parent[i]);
+            }
+            cells.push(othersTime.toFixed(3));
+            cells[level] = 'others';
+            var cols = createRow(table, 'td', cells);
+            for (i = 0; i < level; i++) {
+                cols[i].className = 'muted';
             }
 
-            return childrenRows;
-        };
+            var cell = cols[level];
+            var tr = cell.parentNode;
+            var onclick = function() {
+                tr.classList.add("hidden");
+                cell.classList.remove("link");
+                cell.removeEventListener("click", onclick);
+                othersRows.forEach(function(x) {
+                    x.classList.remove("hidden");
+                });
+            };
 
-        addLevel(0, []);
+            cell.title = othersList.join(", ");
+            cell.classList.add("link");
+            cell.addEventListener("click", onclick);
 
+            if (hide) {
+                tr.classList.add("hidden");
+            }
+
+            childrenRows.push(tr);
+        }
+
+        return childrenRows;
+    };
+
+    addLevel(0, []);
+
+    return table;
+}
+
+function showProfile(path, cutoff = 0.05) {
+    requestGet(path, {}, function(data) {
+        data.records['total'] = data.total;
+        const table = createVisualizationTable(data.records, cutoff, "number");
         popup(table);
     });
 }

javascript/progressbar.js

@@ -45,8 +45,15 @@ function formatTime(secs) {
     }
 }
 
+
+var originalAppTitle = undefined;
+
+onUiLoaded(function() {
+    originalAppTitle = document.title;
+});
+
 function setTitle(progress) {
-    var title = 'Stable Diffusion';
+    var title = originalAppTitle;
 
     if (opts.show_progress_in_title && progress) {
         title = '[' + progress.trim() + '] ' + title;
@@ -69,6 +76,26 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     var dateStart = new Date();
     var wasEverActive = false;
     var parentProgressbar = progressbarContainer.parentNode;
+    var wakeLock = null;
+
+    var requestWakeLock = async function() {
+        if (!opts.prevent_screen_sleep_during_generation || wakeLock) return;
+        try {
+            wakeLock = await navigator.wakeLock.request('screen');
+        } catch (err) {
+            console.error('Wake Lock is not supported.');
+        }
+    };
+
+    var releaseWakeLock = async function() {
+        if (!opts.prevent_screen_sleep_during_generation || !wakeLock) return;
+        try {
+            await wakeLock.release();
+            wakeLock = null;
+        } catch (err) {
+            console.error('Wake Lock release failed', err);
+        }
+    };
 
     var divProgress = document.createElement('div');
     divProgress.className = 'progressDiv';
@@ -82,6 +109,7 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     var livePreview = null;
 
     var removeProgressBar = function() {
+        releaseWakeLock();
         if (!divProgress) return;
 
         setTitle("");
@@ -93,6 +121,7 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     };
 
     var funProgress = function(id_task) {
+        requestWakeLock();
         request("./internal/progress", {id_task: id_task, live_preview: false}, function(res) {
             if (res.completed) {
                 removeProgressBar();

javascript/resizeHandle.js

@@ -1,8 +1,8 @@
 (function() {
     const GRADIO_MIN_WIDTH = 320;
-    const GRID_TEMPLATE_COLUMNS = '1fr 16px 1fr';
     const PAD = 16;
     const DEBOUNCE_TIME = 100;
+    const DOUBLE_TAP_DELAY = 200; //ms
 
     const R = {
         tracking: false,
@@ -11,6 +11,7 @@
         leftCol: null,
         leftColStartWidth: null,
         screenX: null,
+        lastTapTime: null,
     };
 
     let resizeTimer;
@@ -21,30 +22,29 @@
     }
 
     function displayResizeHandle(parent) {
+        if (!parent.needHideOnMoblie) {
+            return true;
+        }
         if (window.innerWidth < GRADIO_MIN_WIDTH * 2 + PAD * 4) {
             parent.style.display = 'flex';
-            if (R.handle != null) {
-                R.handle.style.opacity = '0';
-            }
+            parent.resizeHandle.style.display = "none";
             return false;
         } else {
             parent.style.display = 'grid';
-            if (R.handle != null) {
-                R.handle.style.opacity = '100';
-            }
+            parent.resizeHandle.style.display = "block";
             return true;
         }
     }
 
     function afterResize(parent) {
-        if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != GRID_TEMPLATE_COLUMNS) {
+        if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != parent.style.originalGridTemplateColumns) {
             const oldParentWidth = R.parentWidth;
             const newParentWidth = parent.offsetWidth;
             const widthL = parseInt(parent.style.gridTemplateColumns.split(' ')[0]);
 
             const ratio = newParentWidth / oldParentWidth;
 
-            const newWidthL = Math.max(Math.floor(ratio * widthL), GRADIO_MIN_WIDTH);
+            const newWidthL = Math.max(Math.floor(ratio * widthL), parent.minLeftColWidth);
             setLeftColGridTemplate(parent, newWidthL);
 
             R.parentWidth = newParentWidth;
@@ -52,6 +52,14 @@
     }
 
     function setup(parent) {
+
+        function onDoubleClick(evt) {
+            evt.preventDefault();
+            evt.stopPropagation();
+
+            parent.style.gridTemplateColumns = parent.style.originalGridTemplateColumns;
+        }
+
         const leftCol = parent.firstElementChild;
         const rightCol = parent.lastElementChild;
 
@@ -59,63 +67,114 @@
 
         parent.style.display = 'grid';
         parent.style.gap = '0';
-        parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS;
+        let leftColTemplate = "";
+        if (parent.children[0].style.flexGrow) {
+            leftColTemplate = `${parent.children[0].style.flexGrow}fr`;
+            parent.minLeftColWidth = GRADIO_MIN_WIDTH;
+            parent.minRightColWidth = GRADIO_MIN_WIDTH;
+            parent.needHideOnMoblie = true;
+        } else {
+            leftColTemplate = parent.children[0].style.flexBasis;
+            parent.minLeftColWidth = parent.children[0].style.flexBasis.slice(0, -2) / 2;
+            parent.minRightColWidth = 0;
+            parent.needHideOnMoblie = false;
+        }
+
+        if (!leftColTemplate) {
+            leftColTemplate = '1fr';
+        }
+
+        const gridTemplateColumns = `${leftColTemplate} ${PAD}px ${parent.children[1].style.flexGrow}fr`;
+        parent.style.gridTemplateColumns = gridTemplateColumns;
+        parent.style.originalGridTemplateColumns = gridTemplateColumns;
 
         const resizeHandle = document.createElement('div');
         resizeHandle.classList.add('resize-handle');
         parent.insertBefore(resizeHandle, rightCol);
+        parent.resizeHandle = resizeHandle;
 
-        resizeHandle.addEventListener('mousedown', (evt) => {
-            if (evt.button !== 0) return;
+        ['mousedown', 'touchstart'].forEach((eventType) => {
+            resizeHandle.addEventListener(eventType, (evt) => {
+                if (eventType.startsWith('mouse')) {
+                    if (evt.button !== 0) return;
+                } else {
+                    if (evt.changedTouches.length !== 1) return;
 
-            evt.preventDefault();
-            evt.stopPropagation();
+                    const currentTime = new Date().getTime();
+                    if (R.lastTapTime && currentTime - R.lastTapTime <= DOUBLE_TAP_DELAY) {
+                        onDoubleClick(evt);
+                        return;
+                    }
 
-            document.body.classList.add('resizing');
+                    R.lastTapTime = currentTime;
+                }
 
-            R.tracking = true;
-            R.parent = parent;
-            R.parentWidth = parent.offsetWidth;
-            R.handle = resizeHandle;
-            R.leftCol = leftCol;
-            R.leftColStartWidth = leftCol.offsetWidth;
-            R.screenX = evt.screenX;
+                evt.preventDefault();
+                evt.stopPropagation();
+
+                document.body.classList.add('resizing');
+
+                R.tracking = true;
+                R.parent = parent;
+                R.parentWidth = parent.offsetWidth;
+                R.leftCol = leftCol;
+                R.leftColStartWidth = leftCol.offsetWidth;
+                if (eventType.startsWith('mouse')) {
+                    R.screenX = evt.screenX;
+                } else {
+                    R.screenX = evt.changedTouches[0].screenX;
+                }
+            });
         });
 
-        resizeHandle.addEventListener('dblclick', (evt) => {
-            evt.preventDefault();
-            evt.stopPropagation();
-
-            parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS;
-        });
+        resizeHandle.addEventListener('dblclick', onDoubleClick);
 
         afterResize(parent);
     }
 
-    window.addEventListener('mousemove', (evt) => {
-        if (evt.button !== 0) return;
+    ['mousemove', 'touchmove'].forEach((eventType) => {
+        window.addEventListener(eventType, (evt) => {
+            if (eventType.startsWith('mouse')) {
+                if (evt.button !== 0) return;
+            } else {
+                if (evt.changedTouches.length !== 1) return;
+            }
 
-        if (R.tracking) {
-            evt.preventDefault();
-            evt.stopPropagation();
+            if (R.tracking) {
+                if (eventType.startsWith('mouse')) {
+                    evt.preventDefault();
+                }
+                evt.stopPropagation();
 
-            const delta = R.screenX - evt.screenX;
-            const leftColWidth = Math.max(Math.min(R.leftColStartWidth - delta, R.parent.offsetWidth - GRADIO_MIN_WIDTH - PAD), GRADIO_MIN_WIDTH);
-            setLeftColGridTemplate(R.parent, leftColWidth);
-        }
+                let delta = 0;
+                if (eventType.startsWith('mouse')) {
+                    delta = R.screenX - evt.screenX;
+                } else {
+                    delta = R.screenX - evt.changedTouches[0].screenX;
+                }
+                const leftColWidth = Math.max(Math.min(R.leftColStartWidth - delta, R.parent.offsetWidth - R.parent.minRightColWidth - PAD), R.parent.minLeftColWidth);
+                setLeftColGridTemplate(R.parent, leftColWidth);
+            }
+        });
     });
 
-    window.addEventListener('mouseup', (evt) => {
-        if (evt.button !== 0) return;
+    ['mouseup', 'touchend'].forEach((eventType) => {
+        window.addEventListener(eventType, (evt) => {
+            if (eventType.startsWith('mouse')) {
+                if (evt.button !== 0) return;
+            } else {
+                if (evt.changedTouches.length !== 1) return;
+            }
 
-        if (R.tracking) {
-            evt.preventDefault();
-            evt.stopPropagation();
+            if (R.tracking) {
+                evt.preventDefault();
+                evt.stopPropagation();
 
-            R.tracking = false;
+                R.tracking = false;
 
-            document.body.classList.remove('resizing');
-        }
+                document.body.classList.remove('resizing');
+            }
+        });
     });
 
 
@@ -132,10 +191,15 @@
     setupResizeHandle = setup;
 })();
 
-onUiLoaded(function() {
+
+function setupAllResizeHandles() {
     for (var elem of gradioApp().querySelectorAll('.resize-handle-row')) {
-        if (!elem.querySelector('.resize-handle')) {
+        if (!elem.querySelector('.resize-handle') && !elem.children[0].classList.contains("hidden")) {
             setupResizeHandle(elem);
         }
     }
-});
+}
+
+
+onUiLoaded(setupAllResizeHandles);
+

javascript/settings.js

@@ -55,8 +55,8 @@ onOptionsChanged(function() {
     });
 
     opts._categories.forEach(function(x) {
-        var section = x[0];
-        var category = x[1];
+        var section = localization[x[0]] ?? x[0];
+        var category = localization[x[1]] ?? x[1];
 
         var span = document.createElement('SPAN');
         span.textContent = category;

javascript/token-counters.js

@@ -48,11 +48,6 @@ function setupTokenCounting(id, id_counter, id_button) {
     var counter = gradioApp().getElementById(id_counter);
     var textarea = gradioApp().querySelector(`#${id} > label > textarea`);
 
-    if (opts.disable_token_counters) {
-        counter.style.display = "none";
-        return;
-    }
-
     if (counter.parentElement == prompt.parentElement) {
         return;
     }
@@ -61,15 +56,32 @@ function setupTokenCounting(id, id_counter, id_button) {
     prompt.parentElement.style.position = "relative";
 
     var func = onEdit(id, textarea, 800, function() {
-        gradioApp().getElementById(id_button)?.click();
+        if (counter.classList.contains("token-counter-visible")) {
+            gradioApp().getElementById(id_button)?.click();
+        }
     });
     promptTokenCountUpdateFunctions[id] = func;
     promptTokenCountUpdateFunctions[id_button] = func;
 }
 
-function setupTokenCounters() {
-    setupTokenCounting('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button');
-    setupTokenCounting('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button');
-    setupTokenCounting('img2img_prompt', 'img2img_token_counter', 'img2img_token_button');
-    setupTokenCounting('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button');
+function toggleTokenCountingVisibility(id, id_counter, id_button) {
+    var counter = gradioApp().getElementById(id_counter);
+
+    counter.style.display = opts.disable_token_counters ? "none" : "block";
+    counter.classList.toggle("token-counter-visible", !opts.disable_token_counters);
 }
+
+function runCodeForTokenCounters(fun) {
+    fun('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button');
+    fun('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button');
+    fun('img2img_prompt', 'img2img_token_counter', 'img2img_token_button');
+    fun('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button');
+}
+
+onUiLoaded(function() {
+    runCodeForTokenCounters(setupTokenCounting);
+});
+
+onOptionsChanged(function() {
+    runCodeForTokenCounters(toggleTokenCountingVisibility);
+});

javascript/ui.js

@@ -26,6 +26,14 @@ function selected_gallery_index() {
     return all_gallery_buttons().findIndex(elem => elem.classList.contains('selected'));
 }
 
+function gallery_container_buttons(gallery_container) {
+    return gradioApp().querySelectorAll(`#${gallery_container} .thumbnail-item.thumbnail-small`);
+}
+
+function selected_gallery_index_id(gallery_container) {
+    return Array.from(gallery_container_buttons(gallery_container)).findIndex(elem => elem.classList.contains('selected'));
+}
+
 function extract_image_from_gallery(gallery) {
     if (gallery.length == 0) {
         return [null];
@@ -119,16 +127,24 @@ function create_submit_args(args) {
     return res;
 }
 
+function setSubmitButtonsVisibility(tabname, showInterrupt, showSkip, showInterrupting) {
+    gradioApp().getElementById(tabname + '_interrupt').style.display = showInterrupt ? "block" : "none";
+    gradioApp().getElementById(tabname + '_skip').style.display = showSkip ? "block" : "none";
+    gradioApp().getElementById(tabname + '_interrupting').style.display = showInterrupting ? "block" : "none";
+}
+
 function showSubmitButtons(tabname, show) {
-    gradioApp().getElementById(tabname + '_interrupt').style.display = show ? "none" : "block";
-    gradioApp().getElementById(tabname + '_skip').style.display = show ? "none" : "block";
+    setSubmitButtonsVisibility(tabname, !show, !show, false);
+}
+
+function showSubmitInterruptingPlaceholder(tabname) {
+    setSubmitButtonsVisibility(tabname, false, true, true);
 }
 
 function showRestoreProgressButton(tabname, show) {
     var button = gradioApp().getElementById(tabname + "_restore_progress");
     if (!button) return;
-
-    button.style.display = show ? "flex" : "none";
+    button.style.setProperty('display', show ? 'flex' : 'none', 'important');
 }
 
 function submit() {
@@ -150,6 +166,14 @@ function submit() {
     return res;
 }
 
+function submit_txt2img_upscale() {
+    var res = submit(...arguments);
+
+    res[2] = selected_gallery_index();
+
+    return res;
+}
+
 function submit_img2img() {
     showSubmitButtons('img2img', false);
 
@@ -192,6 +216,7 @@ function restoreProgressTxt2img() {
     var id = localGet("txt2img_task_id");
 
     if (id) {
+        showSubmitInterruptingPlaceholder('txt2img');
         requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
             showSubmitButtons('txt2img', true);
         }, null, 0);
@@ -206,6 +231,7 @@ function restoreProgressImg2img() {
     var id = localGet("img2img_task_id");
 
     if (id) {
+        showSubmitInterruptingPlaceholder('img2img');
         requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
             showSubmitButtons('img2img', true);
         }, null, 0);
@@ -215,9 +241,33 @@ function restoreProgressImg2img() {
 }
 
 
+/**
+ * Configure the width and height elements on `tabname` to accept
+ * pasting of resolutions in the form of "width x height".
+ */
+function setupResolutionPasting(tabname) {
+    var width = gradioApp().querySelector(`#${tabname}_width input[type=number]`);
+    var height = gradioApp().querySelector(`#${tabname}_height input[type=number]`);
+    for (const el of [width, height]) {
+        el.addEventListener('paste', function(event) {
+            var pasteData = event.clipboardData.getData('text/plain');
+            var parsed = pasteData.match(/^\s*(\d+)\D+(\d+)\s*$/);
+            if (parsed) {
+                width.value = parsed[1];
+                height.value = parsed[2];
+                updateInput(width);
+                updateInput(height);
+                event.preventDefault();
+            }
+        });
+    }
+}
+
 onUiLoaded(function() {
     showRestoreProgressButton('txt2img', localGet("txt2img_task_id"));
     showRestoreProgressButton('img2img', localGet("img2img_task_id"));
+    setupResolutionPasting('txt2img');
+    setupResolutionPasting('img2img');
 });
 
 
@@ -257,6 +307,7 @@ onAfterUiUpdate(function() {
     var jsdata = textarea.value;
     opts = JSON.parse(jsdata);
 
+    executeCallbacks(optionsAvailableCallbacks); /*global optionsAvailableCallbacks*/
     executeCallbacks(optionsChangedCallbacks); /*global optionsChangedCallbacks*/
 
     Object.defineProperty(textarea, 'value', {
@@ -278,8 +329,6 @@ onAfterUiUpdate(function() {
     });
 
     json_elem.parentElement.style.display = "none";
-
-    setupTokenCounters();
 });
 
 onOptionsChanged(function() {
@@ -297,8 +346,8 @@ onOptionsChanged(function() {
 let txt2img_textarea, img2img_textarea = undefined;
 
 function restart_reload() {
+    document.body.style.backgroundColor = "var(--background-fill-primary)";
     document.body.innerHTML = '<h1 style="font-family:monospace;margin-top:20%;color:lightgray;text-align:center;">Reloading...</h1>';
-
     var requestPing = function() {
         requestGet("./internal/ping", {}, function(data) {
             location.reload();
@@ -372,7 +421,7 @@ function switchWidthHeight(tabname) {
 
 var onEditTimers = {};
 
-// calls func after afterMs milliseconds has passed since the input elem has beed enited by user
+// calls func after afterMs milliseconds has passed since the input elem has been edited by user
 function onEdit(editId, elem, afterMs, func) {
     var edited = function() {
         var existingTimer = onEditTimers[editId];

modules/api/api.py

@@ -17,13 +17,13 @@ from fastapi.encoders import jsonable_encoder
 from secrets import compare_digest
 
 import modules.shared as shared
-from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, generation_parameters_copypaste, sd_models
+from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, infotext_utils, sd_models, sd_schedulers
 from modules.api import models
 from modules.shared import opts
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
 from modules.textual_inversion.textual_inversion import create_embedding, train_embedding
 from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
-from PIL import PngImagePlugin, Image
+from PIL import PngImagePlugin
 from modules.sd_models_config import find_checkpoint_config_near_filename
 from modules.realesrgan_model import get_realesrgan_models
 from modules import devices
@@ -31,7 +31,7 @@ from typing import Any
 import piexif
 import piexif.helper
 from contextlib import closing
-
+from modules.progress import create_task_id, add_task_to_queue, start_task, finish_task, current_task
 
 def script_name_to_index(name, scripts):
     try:
@@ -43,7 +43,7 @@ def script_name_to_index(name, scripts):
 def validate_sampler_name(name):
     config = sd_samplers.all_samplers_map.get(name, None)
     if config is None:
-        raise HTTPException(status_code=404, detail="Sampler not found")
+        raise HTTPException(status_code=400, detail="Sampler not found")
 
     return name
 
@@ -85,7 +85,7 @@ def decode_base64_to_image(encoding):
         headers = {'user-agent': opts.api_useragent} if opts.api_useragent else {}
         response = requests.get(encoding, timeout=30, headers=headers)
         try:
-            image = Image.open(BytesIO(response.content))
+            image = images.read(BytesIO(response.content))
             return image
         except Exception as e:
             raise HTTPException(status_code=500, detail="Invalid image url") from e
@@ -93,7 +93,7 @@ def decode_base64_to_image(encoding):
     if encoding.startswith("data:image/"):
         encoding = encoding.split(";")[1].split(",")[1]
     try:
-        image = Image.open(BytesIO(base64.b64decode(encoding)))
+        image = images.read(BytesIO(base64.b64decode(encoding)))
         return image
     except Exception as e:
         raise HTTPException(status_code=500, detail="Invalid encoded image") from e
@@ -113,7 +113,7 @@ def encode_pil_to_base64(image):
             image.save(output_bytes, format="PNG", pnginfo=(metadata if use_metadata else None), quality=opts.jpeg_quality)
 
         elif opts.samples_format.lower() in ("jpg", "jpeg", "webp"):
-            if image.mode == "RGBA":
+            if image.mode in ("RGBA", "P"):
                 image = image.convert("RGB")
             parameters = image.info.get('parameters', None)
             exif_bytes = piexif.dump({
@@ -221,6 +221,7 @@ class Api:
         self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"])
         self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=models.FlagsModel)
         self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=list[models.SamplerItem])
+        self.add_api_route("/sdapi/v1/schedulers", self.get_schedulers, methods=["GET"], response_model=list[models.SchedulerItem])
         self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=list[models.UpscalerItem])
         self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=list[models.LatentUpscalerModeItem])
         self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=list[models.SDModelItem])
@@ -230,6 +231,7 @@ class Api:
         self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=list[models.RealesrganItem])
         self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=list[models.PromptStyleItem])
         self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse)
+        self.add_api_route("/sdapi/v1/refresh-embeddings", self.refresh_embeddings, methods=["POST"])
         self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"])
         self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"])
         self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse)
@@ -251,6 +253,24 @@ class Api:
         self.default_script_arg_txt2img = []
         self.default_script_arg_img2img = []
 
+        txt2img_script_runner = scripts.scripts_txt2img
+        img2img_script_runner = scripts.scripts_img2img
+
+        if not txt2img_script_runner.scripts or not img2img_script_runner.scripts:
+            ui.create_ui()
+
+        if not txt2img_script_runner.scripts:
+            txt2img_script_runner.initialize_scripts(False)
+        if not self.default_script_arg_txt2img:
+            self.default_script_arg_txt2img = self.init_default_script_args(txt2img_script_runner)
+
+        if not img2img_script_runner.scripts:
+            img2img_script_runner.initialize_scripts(True)
+        if not self.default_script_arg_img2img:
+            self.default_script_arg_img2img = self.init_default_script_args(img2img_script_runner)
+
+
+
     def add_api_route(self, path: str, endpoint, **kwargs):
         if shared.cmd_opts.api_auth:
             return self.app.add_api_route(path, endpoint, dependencies=[Depends(self.auth)], **kwargs)
@@ -312,8 +332,13 @@ class Api:
                     script_args[script.args_from:script.args_to] = ui_default_values
         return script_args
 
-    def init_script_args(self, request, default_script_args, selectable_scripts, selectable_idx, script_runner):
+    def init_script_args(self, request, default_script_args, selectable_scripts, selectable_idx, script_runner, *, input_script_args=None):
         script_args = default_script_args.copy()
+
+        if input_script_args is not None:
+            for index, value in input_script_args.items():
+                script_args[index] = value
+
         # position 0 in script_arg is the idx+1 of the selectable script that is going to be run when using scripts.scripts_*2img.run()
         if selectable_scripts:
             script_args[selectable_scripts.args_from:selectable_scripts.args_to] = request.script_args
@@ -335,33 +360,110 @@ class Api:
                         script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx]
         return script_args
 
+    def apply_infotext(self, request, tabname, *, script_runner=None, mentioned_script_args=None):
+        """Processes `infotext` field from the `request`, and sets other fields of the `request` according to what's in infotext.
+
+        If request already has a field set, and that field is encountered in infotext too, the value from infotext is ignored.
+
+        Additionally, fills `mentioned_script_args` dict with index: value pairs for script arguments read from infotext.
+        """
+
+        if not request.infotext:
+            return {}
+
+        possible_fields = infotext_utils.paste_fields[tabname]["fields"]
+        set_fields = request.model_dump(exclude_unset=True) if hasattr(request, "request") else request.dict(exclude_unset=True)  # pydantic v1/v2 have different names for this
+        params = infotext_utils.parse_generation_parameters(request.infotext)
+
+        def get_field_value(field, params):
+            value = field.function(params) if field.function else params.get(field.label)
+            if value is None:
+                return None
+
+            if field.api in request.__fields__:
+                target_type = request.__fields__[field.api].type_
+            else:
+                target_type = type(field.component.value)
+
+            if target_type == type(None):
+                return None
+
+            if isinstance(value, dict) and value.get('__type__') == 'generic_update':  # this is a gradio.update rather than a value
+                value = value.get('value')
+
+            if value is not None and not isinstance(value, target_type):
+                value = target_type(value)
+
+            return value
+
+        for field in possible_fields:
+            if not field.api:
+                continue
+
+            if field.api in set_fields:
+                continue
+
+            value = get_field_value(field, params)
+            if value is not None:
+                setattr(request, field.api, value)
+
+        if request.override_settings is None:
+            request.override_settings = {}
+
+        overridden_settings = infotext_utils.get_override_settings(params)
+        for _, setting_name, value in overridden_settings:
+            if setting_name not in request.override_settings:
+                request.override_settings[setting_name] = value
+
+        if script_runner is not None and mentioned_script_args is not None:
+            indexes = {v: i for i, v in enumerate(script_runner.inputs)}
+            script_fields = ((field, indexes[field.component]) for field in possible_fields if field.component in indexes)
+
+            for field, index in script_fields:
+                value = get_field_value(field, params)
+
+                if value is None:
+                    continue
+
+                mentioned_script_args[index] = value
+
+        return params
+
     def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI):
+        task_id = txt2imgreq.force_task_id or create_task_id("txt2img")
+
         script_runner = scripts.scripts_txt2img
-        if not script_runner.scripts:
-            script_runner.initialize_scripts(False)
-            ui.create_ui()
-        if not self.default_script_arg_txt2img:
-            self.default_script_arg_txt2img = self.init_default_script_args(script_runner)
+
+        infotext_script_args = {}
+        self.apply_infotext(txt2imgreq, "txt2img", script_runner=script_runner, mentioned_script_args=infotext_script_args)
+
         selectable_scripts, selectable_script_idx = self.get_selectable_script(txt2imgreq.script_name, script_runner)
+        sampler, scheduler = sd_samplers.get_sampler_and_scheduler(txt2imgreq.sampler_name or txt2imgreq.sampler_index, txt2imgreq.scheduler)
 
         populate = txt2imgreq.copy(update={  # Override __init__ params
-            "sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index),
+            "sampler_name": validate_sampler_name(sampler),
             "do_not_save_samples": not txt2imgreq.save_images,
             "do_not_save_grid": not txt2imgreq.save_images,
         })
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
+        if not populate.scheduler and scheduler != "Automatic":
+            populate.scheduler = scheduler
+
         args = vars(populate)
         args.pop('script_name', None)
         args.pop('script_args', None) # will refeed them to the pipeline directly after initializing them
         args.pop('alwayson_scripts', None)
+        args.pop('infotext', None)
 
-        script_args = self.init_script_args(txt2imgreq, self.default_script_arg_txt2img, selectable_scripts, selectable_script_idx, script_runner)
+        script_args = self.init_script_args(txt2imgreq, self.default_script_arg_txt2img, selectable_scripts, selectable_script_idx, script_runner, input_script_args=infotext_script_args)
 
         send_images = args.pop('send_images', True)
         args.pop('save_images', None)
 
+        add_task_to_queue(task_id)
+
         with self.queue_lock:
             with closing(StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)) as p:
                 p.is_api = True
@@ -371,12 +473,14 @@ class Api:
 
                 try:
                     shared.state.begin(job="scripts_txt2img")
+                    start_task(task_id)
                     if selectable_scripts is not None:
                         p.script_args = script_args
                         processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here
                     else:
                         p.script_args = tuple(script_args) # Need to pass args as tuple here
                         processed = process_images(p)
+                    finish_task(task_id)
                 finally:
                     shared.state.end()
                     shared.total_tqdm.clear()
@@ -386,6 +490,8 @@ class Api:
         return models.TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
 
     def img2imgapi(self, img2imgreq: models.StableDiffusionImg2ImgProcessingAPI):
+        task_id = img2imgreq.force_task_id or create_task_id("img2img")
+
         init_images = img2imgreq.init_images
         if init_images is None:
             raise HTTPException(status_code=404, detail="Init image not found")
@@ -395,15 +501,15 @@ class Api:
             mask = decode_base64_to_image(mask)
 
         script_runner = scripts.scripts_img2img
-        if not script_runner.scripts:
-            script_runner.initialize_scripts(True)
-            ui.create_ui()
-        if not self.default_script_arg_img2img:
-            self.default_script_arg_img2img = self.init_default_script_args(script_runner)
+
+        infotext_script_args = {}
+        self.apply_infotext(img2imgreq, "img2img", script_runner=script_runner, mentioned_script_args=infotext_script_args)
+
         selectable_scripts, selectable_script_idx = self.get_selectable_script(img2imgreq.script_name, script_runner)
+        sampler, scheduler = sd_samplers.get_sampler_and_scheduler(img2imgreq.sampler_name or img2imgreq.sampler_index, img2imgreq.scheduler)
 
         populate = img2imgreq.copy(update={  # Override __init__ params
-            "sampler_name": validate_sampler_name(img2imgreq.sampler_name or img2imgreq.sampler_index),
+            "sampler_name": validate_sampler_name(sampler),
             "do_not_save_samples": not img2imgreq.save_images,
             "do_not_save_grid": not img2imgreq.save_images,
             "mask": mask,
@@ -411,17 +517,23 @@ class Api:
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
+        if not populate.scheduler and scheduler != "Automatic":
+            populate.scheduler = scheduler
+
         args = vars(populate)
         args.pop('include_init_images', None)  # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine.
         args.pop('script_name', None)
         args.pop('script_args', None)  # will refeed them to the pipeline directly after initializing them
         args.pop('alwayson_scripts', None)
+        args.pop('infotext', None)
 
-        script_args = self.init_script_args(img2imgreq, self.default_script_arg_img2img, selectable_scripts, selectable_script_idx, script_runner)
+        script_args = self.init_script_args(img2imgreq, self.default_script_arg_img2img, selectable_scripts, selectable_script_idx, script_runner, input_script_args=infotext_script_args)
 
         send_images = args.pop('send_images', True)
         args.pop('save_images', None)
 
+        add_task_to_queue(task_id)
+
         with self.queue_lock:
             with closing(StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)) as p:
                 p.init_images = [decode_base64_to_image(x) for x in init_images]
@@ -432,12 +544,14 @@ class Api:
 
                 try:
                     shared.state.begin(job="scripts_img2img")
+                    start_task(task_id)
                     if selectable_scripts is not None:
                         p.script_args = script_args
                         processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here
                     else:
                         p.script_args = tuple(script_args) # Need to pass args as tuple here
                         processed = process_images(p)
+                    finish_task(task_id)
                 finally:
                     shared.state.end()
                     shared.total_tqdm.clear()
@@ -480,7 +594,7 @@ class Api:
         if geninfo is None:
             geninfo = ""
 
-        params = generation_parameters_copypaste.parse_generation_parameters(geninfo)
+        params = infotext_utils.parse_generation_parameters(geninfo)
         script_callbacks.infotext_pasted_callback(geninfo, params)
 
         return models.PNGInfoResponse(info=geninfo, items=items, parameters=params)
@@ -511,7 +625,7 @@ class Api:
         if shared.state.current_image and not req.skip_current_image:
             current_image = encode_pil_to_base64(shared.state.current_image)
 
-        return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo)
+        return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo, current_task=current_task)
 
     def interrogateapi(self, interrogatereq: models.InterrogateRequest):
         image_b64 = interrogatereq.image
@@ -578,6 +692,17 @@ class Api:
     def get_samplers(self):
         return [{"name": sampler[0], "aliases":sampler[2], "options":sampler[3]} for sampler in sd_samplers.all_samplers]
 
+    def get_schedulers(self):
+        return [
+            {
+                "name": scheduler.name,
+                "label": scheduler.label,
+                "aliases": scheduler.aliases,
+                "default_rho": scheduler.default_rho,
+                "need_inner_model": scheduler.need_inner_model,
+            }
+            for scheduler in sd_schedulers.schedulers]
+
     def get_upscalers(self):
         return [
             {
@@ -643,6 +768,10 @@ class Api:
             "skipped": convert_embeddings(db.skipped_embeddings),
         }
 
+    def refresh_embeddings(self):
+        with self.queue_lock:
+            sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)
+
     def refresh_checkpoints(self):
         with self.queue_lock:
             shared.refresh_checkpoints()
@@ -775,7 +904,15 @@ class Api:
 
     def launch(self, server_name, port, root_path):
         self.app.include_router(self.router)
-        uvicorn.run(self.app, host=server_name, port=port, timeout_keep_alive=shared.cmd_opts.timeout_keep_alive, root_path=root_path)
+        uvicorn.run(
+            self.app,
+            host=server_name,
+            port=port,
+            timeout_keep_alive=shared.cmd_opts.timeout_keep_alive,
+            root_path=root_path,
+            ssl_keyfile=shared.cmd_opts.tls_keyfile,
+            ssl_certfile=shared.cmd_opts.tls_certfile
+        )
 
     def kill_webui(self):
         restart.stop_program()

modules/api/models.py

@@ -107,6 +107,8 @@ StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
         {"key": "send_images", "type": bool, "default": True},
         {"key": "save_images", "type": bool, "default": False},
         {"key": "alwayson_scripts", "type": dict, "default": {}},
+        {"key": "force_task_id", "type": str, "default": None},
+        {"key": "infotext", "type": str, "default": None},
     ]
 ).generate_model()
 
@@ -124,6 +126,8 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
         {"key": "send_images", "type": bool, "default": True},
         {"key": "save_images", "type": bool, "default": False},
         {"key": "alwayson_scripts", "type": dict, "default": {}},
+        {"key": "force_task_id", "type": str, "default": None},
+        {"key": "infotext", "type": str, "default": None},
     ]
 ).generate_model()
 
@@ -143,7 +147,7 @@ class ExtrasBaseRequest(BaseModel):
     gfpgan_visibility: float = Field(default=0, title="GFPGAN Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of GFPGAN, values should be between 0 and 1.")
     codeformer_visibility: float = Field(default=0, title="CodeFormer Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of CodeFormer, values should be between 0 and 1.")
     codeformer_weight: float = Field(default=0, title="CodeFormer Weight", ge=0, le=1, allow_inf_nan=False, description="Sets the weight of CodeFormer, values should be between 0 and 1.")
-    upscaling_resize: float = Field(default=2, title="Upscaling Factor", ge=1, le=8, description="By how much to upscale the image, only used when resize_mode=0.")
+    upscaling_resize: float = Field(default=2, title="Upscaling Factor", gt=0, description="By how much to upscale the image, only used when resize_mode=0.")
     upscaling_resize_w: int = Field(default=512, title="Target Width", ge=1, description="Target width for the upscaler to hit. Only used when resize_mode=1.")
     upscaling_resize_h: int = Field(default=512, title="Target Height", ge=1, description="Target height for the upscaler to hit. Only used when resize_mode=1.")
     upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the chosen size?")
@@ -231,6 +235,13 @@ class SamplerItem(BaseModel):
     aliases: list[str] = Field(title="Aliases")
     options: dict[str, str] = Field(title="Options")
 
+class SchedulerItem(BaseModel):
+    name: str = Field(title="Name")
+    label: str = Field(title="Label")
+    aliases: Optional[list[str]] = Field(title="Aliases")
+    default_rho: Optional[float] = Field(title="Default Rho")
+    need_inner_model: Optional[bool] = Field(title="Needs Inner Model")
+
 class UpscalerItem(BaseModel):
     name: str = Field(title="Name")
     model_name: Optional[str] = Field(title="Model Name")

modules/cache.py

@@ -2,48 +2,55 @@ import json
 import os
 import os.path
 import threading
-import time
+
+import diskcache
+import tqdm
 
 from modules.paths import data_path, script_path
 
 cache_filename = os.environ.get('SD_WEBUI_CACHE_FILE', os.path.join(data_path, "cache.json"))
-cache_data = None
+cache_dir = os.environ.get('SD_WEBUI_CACHE_DIR', os.path.join(data_path, "cache"))
+caches = {}
 cache_lock = threading.Lock()
 
-dump_cache_after = None
-dump_cache_thread = None
-
 
 def dump_cache():
-    """
-    Marks cache for writing to disk. 5 seconds after no one else flags the cache for writing, it is written.
-    """
+    """old function for dumping cache to disk; does nothing since diskcache."""
 
-    global dump_cache_after
-    global dump_cache_thread
+    pass
 
-    def thread_func():
-        global dump_cache_after
-        global dump_cache_thread
 
-        while dump_cache_after is not None and time.time() < dump_cache_after:
-            time.sleep(1)
+def make_cache(subsection: str) -> diskcache.Cache:
+    return diskcache.Cache(
+        os.path.join(cache_dir, subsection),
+        size_limit=2**32,  # 4 GB, culling oldest first
+        disk_min_file_size=2**18,  # keep up to 256KB in Sqlite
+    )
 
-        with cache_lock:
-            cache_filename_tmp = cache_filename + "-"
-            with open(cache_filename_tmp, "w", encoding="utf8") as file:
-                json.dump(cache_data, file, indent=4, ensure_ascii=False)
 
-            os.replace(cache_filename_tmp, cache_filename)
+def convert_old_cached_data():
+    try:
+        with open(cache_filename, "r", encoding="utf8") as file:
+            data = json.load(file)
+    except FileNotFoundError:
+        return
+    except Exception:
+        os.replace(cache_filename, os.path.join(script_path, "tmp", "cache.json"))
+        print('[ERROR] issue occurred while trying to read cache.json; old cache has been moved to tmp/cache.json')
+        return
 
-            dump_cache_after = None
-            dump_cache_thread = None
+    total_count = sum(len(keyvalues) for keyvalues in data.values())
 
-    with cache_lock:
-        dump_cache_after = time.time() + 5
-        if dump_cache_thread is None:
-            dump_cache_thread = threading.Thread(name='cache-writer', target=thread_func)
-            dump_cache_thread.start()
+    with tqdm.tqdm(total=total_count, desc="converting cache") as progress:
+        for subsection, keyvalues in data.items():
+            cache_obj = caches.get(subsection)
+            if cache_obj is None:
+                cache_obj = make_cache(subsection)
+                caches[subsection] = cache_obj
+
+            for key, value in keyvalues.items():
+                cache_obj[key] = value
+                progress.update(1)
 
 
 def cache(subsection):
@@ -54,29 +61,21 @@ def cache(subsection):
         subsection (str): The subsection identifier for the cache.
 
     Returns:
-        dict: The cache data for the specified subsection.
+        diskcache.Cache: The cache data for the specified subsection.
     """
 
-    global cache_data
-
-    if cache_data is None:
+    cache_obj = caches.get(subsection)
+    if not cache_obj:
         with cache_lock:
-            if cache_data is None:
-                if not os.path.isfile(cache_filename):
-                    cache_data = {}
-                else:
-                    try:
-                        with open(cache_filename, "r", encoding="utf8") as file:
-                            cache_data = json.load(file)
-                    except Exception:
-                        os.replace(cache_filename, os.path.join(script_path, "tmp", "cache.json"))
-                        print('[ERROR] issue occurred while trying to read cache.json, move current cache to tmp/cache.json and create new cache')
-                        cache_data = {}
+            if not os.path.exists(cache_dir) and os.path.isfile(cache_filename):
+                convert_old_cached_data()
 
-    s = cache_data.get(subsection, {})
-    cache_data[subsection] = s
+            cache_obj = caches.get(subsection)
+            if not cache_obj:
+                cache_obj = make_cache(subsection)
+                caches[subsection] = cache_obj
 
-    return s
+    return cache_obj
 
 
 def cached_data_for_file(subsection, title, filename, func):

modules/call_queue.py

@@ -1,8 +1,9 @@
+import os.path
 from functools import wraps
 import html
 import time
 
-from modules import shared, progress, errors, devices, fifo_lock
+from modules import shared, progress, errors, devices, fifo_lock, profiling
 
 queue_lock = fifo_lock.FIFOLock()
 
@@ -46,6 +47,22 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
 
 
 def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
+    @wraps(func)
+    def f(*args, **kwargs):
+        try:
+            res = func(*args, **kwargs)
+        finally:
+            shared.state.skipped = False
+            shared.state.interrupted = False
+            shared.state.stopping_generation = False
+            shared.state.job_count = 0
+            shared.state.job = ""
+        return res
+
+    return wrap_gradio_call_no_job(f, extra_outputs, add_stats)
+
+
+def wrap_gradio_call_no_job(func, extra_outputs=None, add_stats=False):
     @wraps(func)
     def f(*args, extra_outputs_array=extra_outputs, **kwargs):
         run_memmon = shared.opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats
@@ -65,9 +82,6 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
                 arg_str += f" (Argument list truncated at {max_debug_str_len}/{len(arg_str)} characters)"
             errors.report(f"{message}\n{arg_str}", exc_info=True)
 
-            shared.state.job = ""
-            shared.state.job_count = 0
-
             if extra_outputs_array is None:
                 extra_outputs_array = [None, '']
 
@@ -76,10 +90,6 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
 
         devices.torch_gc()
 
-        shared.state.skipped = False
-        shared.state.interrupted = False
-        shared.state.job_count = 0
-
         if not add_stats:
             return tuple(res)
 
@@ -99,8 +109,8 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
             sys_pct = sys_peak/max(sys_total, 1) * 100
 
             toltip_a = "Active: peak amount of video memory used during generation (excluding cached data)"
-            toltip_r = "Reserved: total amout of video memory allocated by the Torch library "
-            toltip_sys = "System: peak amout of video memory allocated by all running programs, out of total capacity"
+            toltip_r = "Reserved: total amount of video memory allocated by the Torch library "
+            toltip_sys = "System: peak amount of video memory allocated by all running programs, out of total capacity"
 
             text_a = f"<abbr title='{toltip_a}'>A</abbr>: <span class='measurement'>{active_peak/1024:.2f} GB</span>"
             text_r = f"<abbr title='{toltip_r}'>R</abbr>: <span class='measurement'>{reserved_peak/1024:.2f} GB</span>"
@@ -110,9 +120,15 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
         else:
             vram_html = ''
 
+        if shared.opts.profiling_enable and os.path.exists(shared.opts.profiling_filename):
+            profiling_html = f"<p class='profile'> [ <a href='{profiling.webpath()}' download>Profile</a> ] </p>"
+        else:
+            profiling_html = ''
+
         # last item is always HTML
-        res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr><span class='measurement'>{elapsed_text}</span></p>{vram_html}</div>"
+        res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr><span class='measurement'>{elapsed_text}</span></p>{vram_html}{profiling_html}</div>"
 
         return tuple(res)
 
     return f
+

modules/cmd_args.py

@@ -1,7 +1,7 @@
 import argparse
 import json
 import os
-from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file  # noqa: F401
+from modules.paths_internal import normalized_filepath, models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file  # noqa: F401
 
 parser = argparse.ArgumentParser()
 
@@ -19,21 +19,22 @@ parser.add_argument("--skip-install", action='store_true', help="launch.py argum
 parser.add_argument("--dump-sysinfo", action='store_true', help="launch.py argument: dump limited sysinfo file (without information about extensions, options) to disk and quit")
 parser.add_argument("--loglevel", type=str, help="log level; one of: CRITICAL, ERROR, WARNING, INFO, DEBUG", default=None)
 parser.add_argument("--do-not-download-clip", action='store_true', help="do not download CLIP model even if it's not included in the checkpoint")
-parser.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
-parser.add_argument("--config", type=str, default=sd_default_config, help="path to config which constructs model",)
-parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
-parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
-parser.add_argument("--vae-dir", type=str, default=None, help="Path to directory with VAE files")
-parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
-parser.add_argument("--gfpgan-model", type=str, help="GFPGAN model file name", default=None)
+parser.add_argument("--data-dir", type=normalized_filepath, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
+parser.add_argument("--models-dir", type=normalized_filepath, default=None, help="base path where models are stored; overrides --data-dir")
+parser.add_argument("--config", type=normalized_filepath, default=sd_default_config, help="path to config which constructs model",)
+parser.add_argument("--ckpt", type=normalized_filepath, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
+parser.add_argument("--ckpt-dir", type=normalized_filepath, default=None, help="Path to directory with stable diffusion checkpoints")
+parser.add_argument("--vae-dir", type=normalized_filepath, default=None, help="Path to directory with VAE files")
+parser.add_argument("--gfpgan-dir", type=normalized_filepath, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
+parser.add_argument("--gfpgan-model", type=normalized_filepath, help="GFPGAN model file name", default=None)
 parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")
 parser.add_argument("--no-half-vae", action='store_true', help="do not switch the VAE model to 16-bit floats")
 parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)")
-parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI")
-parser.add_argument("--embeddings-dir", type=str, default=os.path.join(data_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
-parser.add_argument("--textual-inversion-templates-dir", type=str, default=os.path.join(script_path, 'textual_inversion_templates'), help="directory with textual inversion templates")
-parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
-parser.add_argument("--localizations-dir", type=str, default=os.path.join(script_path, 'localizations'), help="localizations directory")
+parser.add_argument("--max-batch-count", type=int, default=16, help="does not do anything")
+parser.add_argument("--embeddings-dir", type=normalized_filepath, default=os.path.join(data_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
+parser.add_argument("--textual-inversion-templates-dir", type=normalized_filepath, default=os.path.join(script_path, 'textual_inversion_templates'), help="directory with textual inversion templates")
+parser.add_argument("--hypernetwork-dir", type=normalized_filepath, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
+parser.add_argument("--localizations-dir", type=normalized_filepath, default=os.path.join(script_path, 'localizations'), help="localizations directory")
 parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui")
 parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage")
 parser.add_argument("--medvram-sdxl", action='store_true', help="enable --medvram optimization just for SDXL models")
@@ -41,19 +42,20 @@ parser.add_argument("--lowvram", action='store_true', help="enable stable diffus
 parser.add_argument("--lowram", action='store_true', help="load stable diffusion checkpoint weights to VRAM instead of RAM")
 parser.add_argument("--always-batch-cond-uncond", action='store_true', help="does not do anything")
 parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
-parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
+parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "half", "autocast"], default="autocast")
 parser.add_argument("--upcast-sampling", action='store_true', help="upcast sampling. No effect with --no-half. Usually produces similar results to --no-half with better performance while using less memory.")
 parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site")
 parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None)
 parser.add_argument("--ngrok-region", type=str, help="does not do anything.", default="")
 parser.add_argument("--ngrok-options", type=json.loads, help='The options to pass to ngrok in JSON format, e.g.: \'{"authtoken_from_env":true, "basic_auth":"user:password", "oauth_provider":"google", "oauth_allow_emails":"user@asdf.com"}\'', default=dict())
 parser.add_argument("--enable-insecure-extension-access", action='store_true', help="enable extensions tab regardless of other options")
-parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
-parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
-parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
-parser.add_argument("--bsrgan-models-path", type=str, help="Path to directory with BSRGAN model file(s).", default=os.path.join(models_path, 'BSRGAN'))
-parser.add_argument("--realesrgan-models-path", type=str, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(models_path, 'RealESRGAN'))
-parser.add_argument("--clip-models-path", type=str, help="Path to directory with CLIP model file(s).", default=None)
+parser.add_argument("--codeformer-models-path", type=normalized_filepath, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
+parser.add_argument("--gfpgan-models-path", type=normalized_filepath, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
+parser.add_argument("--esrgan-models-path", type=normalized_filepath, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
+parser.add_argument("--bsrgan-models-path", type=normalized_filepath, help="Path to directory with BSRGAN model file(s).", default=os.path.join(models_path, 'BSRGAN'))
+parser.add_argument("--realesrgan-models-path", type=normalized_filepath, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(models_path, 'RealESRGAN'))
+parser.add_argument("--dat-models-path", type=normalized_filepath, help="Path to directory with DAT model file(s).", default=os.path.join(models_path, 'DAT'))
+parser.add_argument("--clip-models-path", type=normalized_filepath, help="Path to directory with CLIP model file(s).", default=None)
 parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
 parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
 parser.add_argument("--xformers-flash-attention", action='store_true', help="enable xformers with Flash Attention to improve reproducibility (supported for SD2.x or variant only)")
@@ -77,22 +79,24 @@ parser.add_argument("--port", type=int, help="launch gradio with given server po
 parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
 parser.add_argument("--ui-config-file", type=str, help="filename to use for ui configuration", default=os.path.join(data_path, 'ui-config.json'))
 parser.add_argument("--hide-ui-dir-config", action='store_true', help="hide directory configuration from webui", default=False)
-parser.add_argument("--freeze-settings", action='store_true', help="disable editing settings", default=False)
+parser.add_argument("--freeze-settings", action='store_true', help="disable editing of all settings globally", default=False)
+parser.add_argument("--freeze-settings-in-sections", type=str, help='disable editing settings in specific sections of the settings page by specifying a comma-delimited list such like "saving-images,upscaling". The list of setting names can be found in the modules/shared_options.py file', default=None)
+parser.add_argument("--freeze-specific-settings", type=str, help='disable editing of individual settings by specifying a comma-delimited list like "samples_save,samples_format". The list of setting names can be found in the config.json file', default=None)
 parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default=os.path.join(data_path, 'config.json'))
 parser.add_argument("--gradio-debug",  action='store_true', help="launch gradio with --debug option")
 parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
-parser.add_argument("--gradio-auth-path", type=str, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
+parser.add_argument("--gradio-auth-path", type=normalized_filepath, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
 parser.add_argument("--gradio-img2img-tool", type=str, help='does not do anything')
 parser.add_argument("--gradio-inpaint-tool", type=str, help="does not do anything")
 parser.add_argument("--gradio-allowed-path", action='append', help="add path to gradio's allowed_paths, make it possible to serve files from it", default=[data_path])
 parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
-parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(data_path, 'styles.csv'))
+parser.add_argument("--styles-file", type=str, action='append', help="path or wildcard path of styles files, allow multiple entries.", default=[])
 parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)
 parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
 parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
 parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
 parser.add_argument("--enable-console-prompts", action='store_true', help="does not do anything", default=False)  # Legacy compatibility, use as default value shared.opts.enable_console_prompts
-parser.add_argument('--vae-path', type=str, help='Checkpoint to use as VAE; setting this argument disables all settings related to VAE', default=None)
+parser.add_argument('--vae-path', type=normalized_filepath, help='Checkpoint to use as VAE; setting this argument disables all settings related to VAE', default=None)
 parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
 parser.add_argument("--api", action='store_true', help="use api=True to launch the API together with the webui (use --nowebui instead for only the API)")
 parser.add_argument("--api-auth", type=str, help='Set authentication for API like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
@@ -118,4 +122,7 @@ parser.add_argument('--api-server-stop', action='store_true', help='enable serve
 parser.add_argument('--timeout-keep-alive', type=int, default=30, help='set timeout_keep_alive for uvicorn')
 parser.add_argument("--disable-all-extensions", action='store_true', help="prevent all extensions from running regardless of any other settings", default=False)
 parser.add_argument("--disable-extra-extensions", action='store_true', help="prevent all extensions except built-in from running regardless of any other settings", default=False)
-parser.add_argument("--skip-load-model-at-start", action='store_true', help="if load a model at web start, only take effect when --nowebui", )
+parser.add_argument("--skip-load-model-at-start", action='store_true', help="if load a model at web start, only take effect when --nowebui")
+parser.add_argument("--unix-filenames-sanitization", action='store_true', help="allow any symbols except '/' in filenames. May conflict with your browser and file system")
+parser.add_argument("--filenames-max-length", type=int, default=128, help='maximal length of filenames of saved images. If you override it, it can conflict with your file system')
+parser.add_argument("--no-prompt-history", action='store_true', help="disable read prompt from last generation feature; settings this argument will not create '--data_path/params.txt' file")

modules/codeformer/codeformer_arch.py

@@ -1,276 +0,0 @@
-# this file is copied from CodeFormer repository. Please see comment in modules/codeformer_model.py
-
-import math
-import torch
-from torch import nn, Tensor
-import torch.nn.functional as F
-from typing import Optional
-
-from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock
-from basicsr.utils.registry import ARCH_REGISTRY
-
-def calc_mean_std(feat, eps=1e-5):
-    """Calculate mean and std for adaptive_instance_normalization.
-
-    Args:
-        feat (Tensor): 4D tensor.
-        eps (float): A small value added to the variance to avoid
-            divide-by-zero. Default: 1e-5.
-    """
-    size = feat.size()
-    assert len(size) == 4, 'The input feature should be 4D tensor.'
-    b, c = size[:2]
-    feat_var = feat.view(b, c, -1).var(dim=2) + eps
-    feat_std = feat_var.sqrt().view(b, c, 1, 1)
-    feat_mean = feat.view(b, c, -1).mean(dim=2).view(b, c, 1, 1)
-    return feat_mean, feat_std
-
-
-def adaptive_instance_normalization(content_feat, style_feat):
-    """Adaptive instance normalization.
-
-    Adjust the reference features to have the similar color and illuminations
-    as those in the degradate features.
-
-    Args:
-        content_feat (Tensor): The reference feature.
-        style_feat (Tensor): The degradate features.
-    """
-    size = content_feat.size()
-    style_mean, style_std = calc_mean_std(style_feat)
-    content_mean, content_std = calc_mean_std(content_feat)
-    normalized_feat = (content_feat - content_mean.expand(size)) / content_std.expand(size)
-    return normalized_feat * style_std.expand(size) + style_mean.expand(size)
-
-
-class PositionEmbeddingSine(nn.Module):
-    """
-    This is a more standard version of the position embedding, very similar to the one
-    used by the Attention is all you need paper, generalized to work on images.
-    """
-
-    def __init__(self, num_pos_feats=64, temperature=10000, normalize=False, scale=None):
-        super().__init__()
-        self.num_pos_feats = num_pos_feats
-        self.temperature = temperature
-        self.normalize = normalize
-        if scale is not None and normalize is False:
-            raise ValueError("normalize should be True if scale is passed")
-        if scale is None:
-            scale = 2 * math.pi
-        self.scale = scale
-
-    def forward(self, x, mask=None):
-        if mask is None:
-            mask = torch.zeros((x.size(0), x.size(2), x.size(3)), device=x.device, dtype=torch.bool)
-        not_mask = ~mask
-        y_embed = not_mask.cumsum(1, dtype=torch.float32)
-        x_embed = not_mask.cumsum(2, dtype=torch.float32)
-        if self.normalize:
-            eps = 1e-6
-            y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale
-            x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale
-
-        dim_t = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
-        dim_t = self.temperature ** (2 * (dim_t // 2) / self.num_pos_feats)
-
-        pos_x = x_embed[:, :, :, None] / dim_t
-        pos_y = y_embed[:, :, :, None] / dim_t
-        pos_x = torch.stack(
-            (pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4
-        ).flatten(3)
-        pos_y = torch.stack(
-            (pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4
-        ).flatten(3)
-        pos = torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2)
-        return pos
-
-def _get_activation_fn(activation):
-    """Return an activation function given a string"""
-    if activation == "relu":
-        return F.relu
-    if activation == "gelu":
-        return F.gelu
-    if activation == "glu":
-        return F.glu
-    raise RuntimeError(F"activation should be relu/gelu, not {activation}.")
-
-
-class TransformerSALayer(nn.Module):
-    def __init__(self, embed_dim, nhead=8, dim_mlp=2048, dropout=0.0, activation="gelu"):
-        super().__init__()
-        self.self_attn = nn.MultiheadAttention(embed_dim, nhead, dropout=dropout)
-        # Implementation of Feedforward model - MLP
-        self.linear1 = nn.Linear(embed_dim, dim_mlp)
-        self.dropout = nn.Dropout(dropout)
-        self.linear2 = nn.Linear(dim_mlp, embed_dim)
-
-        self.norm1 = nn.LayerNorm(embed_dim)
-        self.norm2 = nn.LayerNorm(embed_dim)
-        self.dropout1 = nn.Dropout(dropout)
-        self.dropout2 = nn.Dropout(dropout)
-
-        self.activation = _get_activation_fn(activation)
-
-    def with_pos_embed(self, tensor, pos: Optional[Tensor]):
-        return tensor if pos is None else tensor + pos
-
-    def forward(self, tgt,
-                tgt_mask: Optional[Tensor] = None,
-                tgt_key_padding_mask: Optional[Tensor] = None,
-                query_pos: Optional[Tensor] = None):
-
-        # self attention
-        tgt2 = self.norm1(tgt)
-        q = k = self.with_pos_embed(tgt2, query_pos)
-        tgt2 = self.self_attn(q, k, value=tgt2, attn_mask=tgt_mask,
-                              key_padding_mask=tgt_key_padding_mask)[0]
-        tgt = tgt + self.dropout1(tgt2)
-
-        # ffn
-        tgt2 = self.norm2(tgt)
-        tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt2))))
-        tgt = tgt + self.dropout2(tgt2)
-        return tgt
-
-class Fuse_sft_block(nn.Module):
-    def __init__(self, in_ch, out_ch):
-        super().__init__()
-        self.encode_enc = ResBlock(2*in_ch, out_ch)
-
-        self.scale = nn.Sequential(
-                    nn.Conv2d(in_ch, out_ch, kernel_size=3, padding=1),
-                    nn.LeakyReLU(0.2, True),
-                    nn.Conv2d(out_ch, out_ch, kernel_size=3, padding=1))
-
-        self.shift = nn.Sequential(
-                    nn.Conv2d(in_ch, out_ch, kernel_size=3, padding=1),
-                    nn.LeakyReLU(0.2, True),
-                    nn.Conv2d(out_ch, out_ch, kernel_size=3, padding=1))
-
-    def forward(self, enc_feat, dec_feat, w=1):
-        enc_feat = self.encode_enc(torch.cat([enc_feat, dec_feat], dim=1))
-        scale = self.scale(enc_feat)
-        shift = self.shift(enc_feat)
-        residual = w * (dec_feat * scale + shift)
-        out = dec_feat + residual
-        return out
-
-
-@ARCH_REGISTRY.register()
-class CodeFormer(VQAutoEncoder):
-    def __init__(self, dim_embd=512, n_head=8, n_layers=9,
-                codebook_size=1024, latent_size=256,
-                connect_list=('32', '64', '128', '256'),
-                fix_modules=('quantize', 'generator')):
-        super(CodeFormer, self).__init__(512, 64, [1, 2, 2, 4, 4, 8], 'nearest',2, [16], codebook_size)
-
-        if fix_modules is not None:
-            for module in fix_modules:
-                for param in getattr(self, module).parameters():
-                    param.requires_grad = False
-
-        self.connect_list = connect_list
-        self.n_layers = n_layers
-        self.dim_embd = dim_embd
-        self.dim_mlp = dim_embd*2
-
-        self.position_emb = nn.Parameter(torch.zeros(latent_size, self.dim_embd))
-        self.feat_emb = nn.Linear(256, self.dim_embd)
-
-        # transformer
-        self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0)
-                                    for _ in range(self.n_layers)])
-
-        # logits_predict head
-        self.idx_pred_layer = nn.Sequential(
-            nn.LayerNorm(dim_embd),
-            nn.Linear(dim_embd, codebook_size, bias=False))
-
-        self.channels = {
-            '16': 512,
-            '32': 256,
-            '64': 256,
-            '128': 128,
-            '256': 128,
-            '512': 64,
-        }
-
-        # after second residual block for > 16, before attn layer for ==16
-        self.fuse_encoder_block = {'512':2, '256':5, '128':8, '64':11, '32':14, '16':18}
-        # after first residual block for > 16, before attn layer for ==16
-        self.fuse_generator_block = {'16':6, '32': 9, '64':12, '128':15, '256':18, '512':21}
-
-        # fuse_convs_dict
-        self.fuse_convs_dict = nn.ModuleDict()
-        for f_size in self.connect_list:
-            in_ch = self.channels[f_size]
-            self.fuse_convs_dict[f_size] = Fuse_sft_block(in_ch, in_ch)
-
-    def _init_weights(self, module):
-        if isinstance(module, (nn.Linear, nn.Embedding)):
-            module.weight.data.normal_(mean=0.0, std=0.02)
-            if isinstance(module, nn.Linear) and module.bias is not None:
-                module.bias.data.zero_()
-        elif isinstance(module, nn.LayerNorm):
-            module.bias.data.zero_()
-            module.weight.data.fill_(1.0)
-
-    def forward(self, x, w=0, detach_16=True, code_only=False, adain=False):
-        # ################### Encoder #####################
-        enc_feat_dict = {}
-        out_list = [self.fuse_encoder_block[f_size] for f_size in self.connect_list]
-        for i, block in enumerate(self.encoder.blocks):
-            x = block(x)
-            if i in out_list:
-                enc_feat_dict[str(x.shape[-1])] = x.clone()
-
-        lq_feat = x
-        # ################# Transformer ###################
-        # quant_feat, codebook_loss, quant_stats = self.quantize(lq_feat)
-        pos_emb = self.position_emb.unsqueeze(1).repeat(1,x.shape[0],1)
-        # BCHW -> BC(HW) -> (HW)BC
-        feat_emb = self.feat_emb(lq_feat.flatten(2).permute(2,0,1))
-        query_emb = feat_emb
-        # Transformer encoder
-        for layer in self.ft_layers:
-            query_emb = layer(query_emb, query_pos=pos_emb)
-
-        # output logits
-        logits = self.idx_pred_layer(query_emb) # (hw)bn
-        logits = logits.permute(1,0,2) # (hw)bn -> b(hw)n
-
-        if code_only: # for training stage II
-          # logits doesn't need softmax before cross_entropy loss
-            return logits, lq_feat
-
-        # ################# Quantization ###################
-        # if self.training:
-        #     quant_feat = torch.einsum('btn,nc->btc', [soft_one_hot, self.quantize.embedding.weight])
-        #     # b(hw)c -> bc(hw) -> bchw
-        #     quant_feat = quant_feat.permute(0,2,1).view(lq_feat.shape)
-        # ------------
-        soft_one_hot = F.softmax(logits, dim=2)
-        _, top_idx = torch.topk(soft_one_hot, 1, dim=2)
-        quant_feat = self.quantize.get_codebook_feat(top_idx, shape=[x.shape[0],16,16,256])
-        # preserve gradients
-        # quant_feat = lq_feat + (quant_feat - lq_feat).detach()
-
-        if detach_16:
-            quant_feat = quant_feat.detach() # for training stage III
-        if adain:
-            quant_feat = adaptive_instance_normalization(quant_feat, lq_feat)
-
-        # ################## Generator ####################
-        x = quant_feat
-        fuse_list = [self.fuse_generator_block[f_size] for f_size in self.connect_list]
-
-        for i, block in enumerate(self.generator.blocks):
-            x = block(x)
-            if i in fuse_list: # fuse after i-th block
-                f_size = str(x.shape[-1])
-                if w>0:
-                    x = self.fuse_convs_dict[f_size](enc_feat_dict[f_size].detach(), x, w)
-        out = x
-        # logits doesn't need softmax before cross_entropy loss
-        return out, logits, lq_feat

modules/codeformer/vqgan_arch.py

@@ -1,435 +0,0 @@
-# this file is copied from CodeFormer repository. Please see comment in modules/codeformer_model.py
-
-'''
-VQGAN code, adapted from the original created by the Unleashing Transformers authors:
-https://github.com/samb-t/unleashing-transformers/blob/master/models/vqgan.py
-
-'''
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from basicsr.utils import get_root_logger
-from basicsr.utils.registry import ARCH_REGISTRY
-
-def normalize(in_channels):
-    return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
-
-
-@torch.jit.script
-def swish(x):
-    return x*torch.sigmoid(x)
-
-
-#  Define VQVAE classes
-class VectorQuantizer(nn.Module):
-    def __init__(self, codebook_size, emb_dim, beta):
-        super(VectorQuantizer, self).__init__()
-        self.codebook_size = codebook_size  # number of embeddings
-        self.emb_dim = emb_dim  # dimension of embedding
-        self.beta = beta  # commitment cost used in loss term, beta * ||z_e(x)-sg[e]||^2
-        self.embedding = nn.Embedding(self.codebook_size, self.emb_dim)
-        self.embedding.weight.data.uniform_(-1.0 / self.codebook_size, 1.0 / self.codebook_size)
-
-    def forward(self, z):
-        # reshape z -> (batch, height, width, channel) and flatten
-        z = z.permute(0, 2, 3, 1).contiguous()
-        z_flattened = z.view(-1, self.emb_dim)
-
-        # distances from z to embeddings e_j (z - e)^2 = z^2 + e^2 - 2 e * z
-        d = (z_flattened ** 2).sum(dim=1, keepdim=True) + (self.embedding.weight**2).sum(1) - \
-            2 * torch.matmul(z_flattened, self.embedding.weight.t())
-
-        mean_distance = torch.mean(d)
-        # find closest encodings
-        # min_encoding_indices = torch.argmin(d, dim=1).unsqueeze(1)
-        min_encoding_scores, min_encoding_indices = torch.topk(d, 1, dim=1, largest=False)
-        # [0-1], higher score, higher confidence
-        min_encoding_scores = torch.exp(-min_encoding_scores/10)
-
-        min_encodings = torch.zeros(min_encoding_indices.shape[0], self.codebook_size).to(z)
-        min_encodings.scatter_(1, min_encoding_indices, 1)
-
-        # get quantized latent vectors
-        z_q = torch.matmul(min_encodings, self.embedding.weight).view(z.shape)
-        # compute loss for embedding
-        loss = torch.mean((z_q.detach()-z)**2) + self.beta * torch.mean((z_q - z.detach()) ** 2)
-        # preserve gradients
-        z_q = z + (z_q - z).detach()
-
-        # perplexity
-        e_mean = torch.mean(min_encodings, dim=0)
-        perplexity = torch.exp(-torch.sum(e_mean * torch.log(e_mean + 1e-10)))
-        # reshape back to match original input shape
-        z_q = z_q.permute(0, 3, 1, 2).contiguous()
-
-        return z_q, loss, {
-            "perplexity": perplexity,
-            "min_encodings": min_encodings,
-            "min_encoding_indices": min_encoding_indices,
-            "min_encoding_scores": min_encoding_scores,
-            "mean_distance": mean_distance
-            }
-
-    def get_codebook_feat(self, indices, shape):
-        # input indices: batch*token_num -> (batch*token_num)*1
-        # shape: batch, height, width, channel
-        indices = indices.view(-1,1)
-        min_encodings = torch.zeros(indices.shape[0], self.codebook_size).to(indices)
-        min_encodings.scatter_(1, indices, 1)
-        # get quantized latent vectors
-        z_q = torch.matmul(min_encodings.float(), self.embedding.weight)
-
-        if shape is not None:  # reshape back to match original input shape
-            z_q = z_q.view(shape).permute(0, 3, 1, 2).contiguous()
-
-        return z_q
-
-
-class GumbelQuantizer(nn.Module):
-    def __init__(self, codebook_size, emb_dim, num_hiddens, straight_through=False, kl_weight=5e-4, temp_init=1.0):
-        super().__init__()
-        self.codebook_size = codebook_size  # number of embeddings
-        self.emb_dim = emb_dim  # dimension of embedding
-        self.straight_through = straight_through
-        self.temperature = temp_init
-        self.kl_weight = kl_weight
-        self.proj = nn.Conv2d(num_hiddens, codebook_size, 1)  # projects last encoder layer to quantized logits
-        self.embed = nn.Embedding(codebook_size, emb_dim)
-
-    def forward(self, z):
-        hard = self.straight_through if self.training else True
-
-        logits = self.proj(z)
-
-        soft_one_hot = F.gumbel_softmax(logits, tau=self.temperature, dim=1, hard=hard)
-
-        z_q = torch.einsum("b n h w, n d -> b d h w", soft_one_hot, self.embed.weight)
-
-        # + kl divergence to the prior loss
-        qy = F.softmax(logits, dim=1)
-        diff = self.kl_weight * torch.sum(qy * torch.log(qy * self.codebook_size + 1e-10), dim=1).mean()
-        min_encoding_indices = soft_one_hot.argmax(dim=1)
-
-        return z_q, diff, {
-            "min_encoding_indices": min_encoding_indices
-        }
-
-
-class Downsample(nn.Module):
-    def __init__(self, in_channels):
-        super().__init__()
-        self.conv = torch.nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=2, padding=0)
-
-    def forward(self, x):
-        pad = (0, 1, 0, 1)
-        x = torch.nn.functional.pad(x, pad, mode="constant", value=0)
-        x = self.conv(x)
-        return x
-
-
-class Upsample(nn.Module):
-    def __init__(self, in_channels):
-        super().__init__()
-        self.conv = nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=1, padding=1)
-
-    def forward(self, x):
-        x = F.interpolate(x, scale_factor=2.0, mode="nearest")
-        x = self.conv(x)
-
-        return x
-
-
-class ResBlock(nn.Module):
-    def __init__(self, in_channels, out_channels=None):
-        super(ResBlock, self).__init__()
-        self.in_channels = in_channels
-        self.out_channels = in_channels if out_channels is None else out_channels
-        self.norm1 = normalize(in_channels)
-        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1)
-        self.norm2 = normalize(out_channels)
-        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1)
-        if self.in_channels != self.out_channels:
-            self.conv_out = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)
-
-    def forward(self, x_in):
-        x = x_in
-        x = self.norm1(x)
-        x = swish(x)
-        x = self.conv1(x)
-        x = self.norm2(x)
-        x = swish(x)
-        x = self.conv2(x)
-        if self.in_channels != self.out_channels:
-            x_in = self.conv_out(x_in)
-
-        return x + x_in
-
-
-class AttnBlock(nn.Module):
-    def __init__(self, in_channels):
-        super().__init__()
-        self.in_channels = in_channels
-
-        self.norm = normalize(in_channels)
-        self.q = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0
-        )
-        self.k = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0
-        )
-        self.v = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0
-        )
-        self.proj_out = torch.nn.Conv2d(
-            in_channels,
-            in_channels,
-            kernel_size=1,
-            stride=1,
-            padding=0
-        )
-
-    def forward(self, x):
-        h_ = x
-        h_ = self.norm(h_)
-        q = self.q(h_)
-        k = self.k(h_)
-        v = self.v(h_)
-
-        # compute attention
-        b, c, h, w = q.shape
-        q = q.reshape(b, c, h*w)
-        q = q.permute(0, 2, 1)
-        k = k.reshape(b, c, h*w)
-        w_ = torch.bmm(q, k)
-        w_ = w_ * (int(c)**(-0.5))
-        w_ = F.softmax(w_, dim=2)
-
-        # attend to values
-        v = v.reshape(b, c, h*w)
-        w_ = w_.permute(0, 2, 1)
-        h_ = torch.bmm(v, w_)
-        h_ = h_.reshape(b, c, h, w)
-
-        h_ = self.proj_out(h_)
-
-        return x+h_
-
-
-class Encoder(nn.Module):
-    def __init__(self, in_channels, nf, emb_dim, ch_mult, num_res_blocks, resolution, attn_resolutions):
-        super().__init__()
-        self.nf = nf
-        self.num_resolutions = len(ch_mult)
-        self.num_res_blocks = num_res_blocks
-        self.resolution = resolution
-        self.attn_resolutions = attn_resolutions
-
-        curr_res = self.resolution
-        in_ch_mult = (1,)+tuple(ch_mult)
-
-        blocks = []
-        # initial convultion
-        blocks.append(nn.Conv2d(in_channels, nf, kernel_size=3, stride=1, padding=1))
-
-        # residual and downsampling blocks, with attention on smaller res (16x16)
-        for i in range(self.num_resolutions):
-            block_in_ch = nf * in_ch_mult[i]
-            block_out_ch = nf * ch_mult[i]
-            for _ in range(self.num_res_blocks):
-                blocks.append(ResBlock(block_in_ch, block_out_ch))
-                block_in_ch = block_out_ch
-                if curr_res in attn_resolutions:
-                    blocks.append(AttnBlock(block_in_ch))
-
-            if i != self.num_resolutions - 1:
-                blocks.append(Downsample(block_in_ch))
-                curr_res = curr_res // 2
-
-        # non-local attention block
-        blocks.append(ResBlock(block_in_ch, block_in_ch))
-        blocks.append(AttnBlock(block_in_ch))
-        blocks.append(ResBlock(block_in_ch, block_in_ch))
-
-        # normalise and convert to latent size
-        blocks.append(normalize(block_in_ch))
-        blocks.append(nn.Conv2d(block_in_ch, emb_dim, kernel_size=3, stride=1, padding=1))
-        self.blocks = nn.ModuleList(blocks)
-
-    def forward(self, x):
-        for block in self.blocks:
-            x = block(x)
-
-        return x
-
-
-class Generator(nn.Module):
-    def __init__(self, nf, emb_dim, ch_mult, res_blocks, img_size, attn_resolutions):
-        super().__init__()
-        self.nf = nf
-        self.ch_mult = ch_mult
-        self.num_resolutions = len(self.ch_mult)
-        self.num_res_blocks = res_blocks
-        self.resolution = img_size
-        self.attn_resolutions = attn_resolutions
-        self.in_channels = emb_dim
-        self.out_channels = 3
-        block_in_ch = self.nf * self.ch_mult[-1]
-        curr_res = self.resolution // 2 ** (self.num_resolutions-1)
-
-        blocks = []
-        # initial conv
-        blocks.append(nn.Conv2d(self.in_channels, block_in_ch, kernel_size=3, stride=1, padding=1))
-
-        # non-local attention block
-        blocks.append(ResBlock(block_in_ch, block_in_ch))
-        blocks.append(AttnBlock(block_in_ch))
-        blocks.append(ResBlock(block_in_ch, block_in_ch))
-
-        for i in reversed(range(self.num_resolutions)):
-            block_out_ch = self.nf * self.ch_mult[i]
-
-            for _ in range(self.num_res_blocks):
-                blocks.append(ResBlock(block_in_ch, block_out_ch))
-                block_in_ch = block_out_ch
-
-                if curr_res in self.attn_resolutions:
-                    blocks.append(AttnBlock(block_in_ch))
-
-            if i != 0:
-                blocks.append(Upsample(block_in_ch))
-                curr_res = curr_res * 2
-
-        blocks.append(normalize(block_in_ch))
-        blocks.append(nn.Conv2d(block_in_ch, self.out_channels, kernel_size=3, stride=1, padding=1))
-
-        self.blocks = nn.ModuleList(blocks)
-
-
-    def forward(self, x):
-        for block in self.blocks:
-            x = block(x)
-
-        return x
-
-
-@ARCH_REGISTRY.register()
-class VQAutoEncoder(nn.Module):
-    def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=None, codebook_size=1024, emb_dim=256,
-                beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None):
-        super().__init__()
-        logger = get_root_logger()
-        self.in_channels = 3
-        self.nf = nf
-        self.n_blocks = res_blocks
-        self.codebook_size = codebook_size
-        self.embed_dim = emb_dim
-        self.ch_mult = ch_mult
-        self.resolution = img_size
-        self.attn_resolutions = attn_resolutions or [16]
-        self.quantizer_type = quantizer
-        self.encoder = Encoder(
-            self.in_channels,
-            self.nf,
-            self.embed_dim,
-            self.ch_mult,
-            self.n_blocks,
-            self.resolution,
-            self.attn_resolutions
-        )
-        if self.quantizer_type == "nearest":
-            self.beta = beta #0.25
-            self.quantize = VectorQuantizer(self.codebook_size, self.embed_dim, self.beta)
-        elif self.quantizer_type == "gumbel":
-            self.gumbel_num_hiddens = emb_dim
-            self.straight_through = gumbel_straight_through
-            self.kl_weight = gumbel_kl_weight
-            self.quantize = GumbelQuantizer(
-                self.codebook_size,
-                self.embed_dim,
-                self.gumbel_num_hiddens,
-                self.straight_through,
-                self.kl_weight
-            )
-        self.generator = Generator(
-            self.nf,
-            self.embed_dim,
-            self.ch_mult,
-            self.n_blocks,
-            self.resolution,
-            self.attn_resolutions
-        )
-
-        if model_path is not None:
-            chkpt = torch.load(model_path, map_location='cpu')
-            if 'params_ema' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params_ema'])
-                logger.info(f'vqgan is loaded from: {model_path} [params_ema]')
-            elif 'params' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params'])
-                logger.info(f'vqgan is loaded from: {model_path} [params]')
-            else:
-                raise ValueError('Wrong params!')
-
-
-    def forward(self, x):
-        x = self.encoder(x)
-        quant, codebook_loss, quant_stats = self.quantize(x)
-        x = self.generator(quant)
-        return x, codebook_loss, quant_stats
-
-
-
-# patch based discriminator
-@ARCH_REGISTRY.register()
-class VQGANDiscriminator(nn.Module):
-    def __init__(self, nc=3, ndf=64, n_layers=4, model_path=None):
-        super().__init__()
-
-        layers = [nn.Conv2d(nc, ndf, kernel_size=4, stride=2, padding=1), nn.LeakyReLU(0.2, True)]
-        ndf_mult = 1
-        ndf_mult_prev = 1
-        for n in range(1, n_layers):  # gradually increase the number of filters
-            ndf_mult_prev = ndf_mult
-            ndf_mult = min(2 ** n, 8)
-            layers += [
-                nn.Conv2d(ndf * ndf_mult_prev, ndf * ndf_mult, kernel_size=4, stride=2, padding=1, bias=False),
-                nn.BatchNorm2d(ndf * ndf_mult),
-                nn.LeakyReLU(0.2, True)
-            ]
-
-        ndf_mult_prev = ndf_mult
-        ndf_mult = min(2 ** n_layers, 8)
-
-        layers += [
-            nn.Conv2d(ndf * ndf_mult_prev, ndf * ndf_mult, kernel_size=4, stride=1, padding=1, bias=False),
-            nn.BatchNorm2d(ndf * ndf_mult),
-            nn.LeakyReLU(0.2, True)
-        ]
-
-        layers += [
-            nn.Conv2d(ndf * ndf_mult, 1, kernel_size=4, stride=1, padding=1)]  # output 1 channel prediction map
-        self.main = nn.Sequential(*layers)
-
-        if model_path is not None:
-            chkpt = torch.load(model_path, map_location='cpu')
-            if 'params_d' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params_d'])
-            elif 'params' in chkpt:
-                self.load_state_dict(torch.load(model_path, map_location='cpu')['params'])
-            else:
-                raise ValueError('Wrong params!')
-
-    def forward(self, x):
-        return self.main(x)

modules/codeformer_model.py

@@ -1,132 +1,64 @@
-import os
+from __future__ import annotations
+
+import logging
 
-import cv2
 import torch
 
-import modules.face_restoration
-import modules.shared
-from modules import shared, devices, modelloader, errors
-from modules.paths import models_path
+from modules import (
+    devices,
+    errors,
+    face_restoration,
+    face_restoration_utils,
+    modelloader,
+    shared,
+)
+
+logger = logging.getLogger(__name__)
 
-# codeformer people made a choice to include modified basicsr library to their project which makes
-# it utterly impossible to use it alongside with other libraries that also use basicsr, like GFPGAN.
-# I am making a choice to include some files from codeformer to work around this issue.
-model_dir = "Codeformer"
-model_path = os.path.join(models_path, model_dir)
 model_url = 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth'
+model_download_name = 'codeformer-v0.1.0.pth'
 
-codeformer = None
+# used by e.g. postprocessing_codeformer.py
+codeformer: face_restoration.FaceRestoration | None = None
 
 
-def setup_model(dirname):
-    os.makedirs(model_path, exist_ok=True)
+class FaceRestorerCodeFormer(face_restoration_utils.CommonFaceRestoration):
+    def name(self):
+        return "CodeFormer"
 
-    path = modules.paths.paths.get("CodeFormer", None)
-    if path is None:
-        return
+    def load_net(self) -> torch.Module:
+        for model_path in modelloader.load_models(
+            model_path=self.model_path,
+            model_url=model_url,
+            command_path=self.model_path,
+            download_name=model_download_name,
+            ext_filter=['.pth'],
+        ):
+            return modelloader.load_spandrel_model(
+                model_path,
+                device=devices.device_codeformer,
+                expected_architecture='CodeFormer',
+            ).model
+        raise ValueError("No codeformer model found")
 
+    def get_device(self):
+        return devices.device_codeformer
+
+    def restore(self, np_image, w: float | None = None):
+        if w is None:
+            w = getattr(shared.opts, "code_former_weight", 0.5)
+
+        def restore_face(cropped_face_t):
+            assert self.net is not None
+            return self.net(cropped_face_t, weight=w, adain=True)[0]
+
+        return self.restore_with_helper(np_image, restore_face)
+
+
+def setup_model(dirname: str) -> None:
+    global codeformer
     try:
-        from torchvision.transforms.functional import normalize
-        from modules.codeformer.codeformer_arch import CodeFormer
-        from basicsr.utils import img2tensor, tensor2img
-        from facelib.utils.face_restoration_helper import FaceRestoreHelper
-        from facelib.detection.retinaface import retinaface
-
-        net_class = CodeFormer
-
-        class FaceRestorerCodeFormer(modules.face_restoration.FaceRestoration):
-            def name(self):
-                return "CodeFormer"
-
-            def __init__(self, dirname):
-                self.net = None
-                self.face_helper = None
-                self.cmd_dir = dirname
-
-            def create_models(self):
-
-                if self.net is not None and self.face_helper is not None:
-                    self.net.to(devices.device_codeformer)
-                    return self.net, self.face_helper
-                model_paths = modelloader.load_models(model_path, model_url, self.cmd_dir, download_name='codeformer-v0.1.0.pth', ext_filter=['.pth'])
-                if len(model_paths) != 0:
-                    ckpt_path = model_paths[0]
-                else:
-                    print("Unable to load codeformer model.")
-                    return None, None
-                net = net_class(dim_embd=512, codebook_size=1024, n_head=8, n_layers=9, connect_list=['32', '64', '128', '256']).to(devices.device_codeformer)
-                checkpoint = torch.load(ckpt_path)['params_ema']
-                net.load_state_dict(checkpoint)
-                net.eval()
-
-                if hasattr(retinaface, 'device'):
-                    retinaface.device = devices.device_codeformer
-                face_helper = FaceRestoreHelper(1, face_size=512, crop_ratio=(1, 1), det_model='retinaface_resnet50', save_ext='png', use_parse=True, device=devices.device_codeformer)
-
-                self.net = net
-                self.face_helper = face_helper
-
-                return net, face_helper
-
-            def send_model_to(self, device):
-                self.net.to(device)
-                self.face_helper.face_det.to(device)
-                self.face_helper.face_parse.to(device)
-
-            def restore(self, np_image, w=None):
-                np_image = np_image[:, :, ::-1]
-
-                original_resolution = np_image.shape[0:2]
-
-                self.create_models()
-                if self.net is None or self.face_helper is None:
-                    return np_image
-
-                self.send_model_to(devices.device_codeformer)
-
-                self.face_helper.clean_all()
-                self.face_helper.read_image(np_image)
-                self.face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5)
-                self.face_helper.align_warp_face()
-
-                for cropped_face in self.face_helper.cropped_faces:
-                    cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True)
-                    normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
-                    cropped_face_t = cropped_face_t.unsqueeze(0).to(devices.device_codeformer)
-
-                    try:
-                        with torch.no_grad():
-                            output = self.net(cropped_face_t, w=w if w is not None else shared.opts.code_former_weight, adain=True)[0]
-                            restored_face = tensor2img(output, rgb2bgr=True, min_max=(-1, 1))
-                        del output
-                        devices.torch_gc()
-                    except Exception:
-                        errors.report('Failed inference for CodeFormer', exc_info=True)
-                        restored_face = tensor2img(cropped_face_t, rgb2bgr=True, min_max=(-1, 1))
-
-                    restored_face = restored_face.astype('uint8')
-                    self.face_helper.add_restored_face(restored_face)
-
-                self.face_helper.get_inverse_affine(None)
-
-                restored_img = self.face_helper.paste_faces_to_input_image()
-                restored_img = restored_img[:, :, ::-1]
-
-                if original_resolution != restored_img.shape[0:2]:
-                    restored_img = cv2.resize(restored_img, (0, 0), fx=original_resolution[1]/restored_img.shape[1], fy=original_resolution[0]/restored_img.shape[0], interpolation=cv2.INTER_LINEAR)
-
-                self.face_helper.clean_all()
-
-                if shared.opts.face_restoration_unload:
-                    self.send_model_to(devices.cpu)
-
-                return restored_img
-
-        global codeformer
         codeformer = FaceRestorerCodeFormer(dirname)
         shared.face_restorers.append(codeformer)
-
     except Exception:
         errors.report("Error setting up CodeFormer", exc_info=True)
-
-   # sys.path = stored_sys_path

modules/dat_model.py

@@ -0,0 +1,79 @@
+import os
+
+from modules import modelloader, errors
+from modules.shared import cmd_opts, opts
+from modules.upscaler import Upscaler, UpscalerData
+from modules.upscaler_utils import upscale_with_model
+
+
+class UpscalerDAT(Upscaler):
+    def __init__(self, user_path):
+        self.name = "DAT"
+        self.user_path = user_path
+        self.scalers = []
+        super().__init__()
+
+        for file in self.find_models(ext_filter=[".pt", ".pth"]):
+            name = modelloader.friendly_name(file)
+            scaler_data = UpscalerData(name, file, upscaler=self, scale=None)
+            self.scalers.append(scaler_data)
+
+        for model in get_dat_models(self):
+            if model.name in opts.dat_enabled_models:
+                self.scalers.append(model)
+
+    def do_upscale(self, img, path):
+        try:
+            info = self.load_model(path)
+        except Exception:
+            errors.report(f"Unable to load DAT model {path}", exc_info=True)
+            return img
+
+        model_descriptor = modelloader.load_spandrel_model(
+            info.local_data_path,
+            device=self.device,
+            prefer_half=(not cmd_opts.no_half and not cmd_opts.upcast_sampling),
+            expected_architecture="DAT",
+        )
+        return upscale_with_model(
+            model_descriptor,
+            img,
+            tile_size=opts.DAT_tile,
+            tile_overlap=opts.DAT_tile_overlap,
+        )
+
+    def load_model(self, path):
+        for scaler in self.scalers:
+            if scaler.data_path == path:
+                if scaler.local_data_path.startswith("http"):
+                    scaler.local_data_path = modelloader.load_file_from_url(
+                        scaler.data_path,
+                        model_dir=self.model_download_path,
+                    )
+                if not os.path.exists(scaler.local_data_path):
+                    raise FileNotFoundError(f"DAT data missing: {scaler.local_data_path}")
+                return scaler
+        raise ValueError(f"Unable to find model info: {path}")
+
+
+def get_dat_models(scaler):
+    return [
+        UpscalerData(
+            name="DAT x2",
+            path="https://github.com/n0kovo/dat_upscaler_models/raw/main/DAT/DAT_x2.pth",
+            scale=2,
+            upscaler=scaler,
+        ),
+        UpscalerData(
+            name="DAT x3",
+            path="https://github.com/n0kovo/dat_upscaler_models/raw/main/DAT/DAT_x3.pth",
+            scale=3,
+            upscaler=scaler,
+        ),
+        UpscalerData(
+            name="DAT x4",
+            path="https://github.com/n0kovo/dat_upscaler_models/raw/main/DAT/DAT_x4.pth",
+            scale=4,
+            upscaler=scaler,
+        ),
+    ]

modules/deepbooru.py

@@ -57,7 +57,7 @@ class DeepDanbooru:
         a = np.expand_dims(np.array(pic, dtype=np.float32), 0) / 255
 
         with torch.no_grad(), devices.autocast():
-            x = torch.from_numpy(a).to(devices.device)
+            x = torch.from_numpy(a).to(devices.device, devices.dtype)
             y = self.model(x)[0].detach().cpu().numpy()
 
         probability_dict = {}

modules/devices.py

@@ -3,7 +3,7 @@ import contextlib
 from functools import lru_cache
 
 import torch
-from modules import errors, shared
+from modules import errors, shared, npu_specific
 
 if sys.platform == "darwin":
     from modules import mac_specific
@@ -23,6 +23,23 @@ def has_mps() -> bool:
         return mac_specific.has_mps
 
 
+def cuda_no_autocast(device_id=None) -> bool:
+    if device_id is None:
+        device_id = get_cuda_device_id()
+    return (
+        torch.cuda.get_device_capability(device_id) == (7, 5)
+        and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16")
+    )
+
+
+def get_cuda_device_id():
+    return (
+        int(shared.cmd_opts.device_id)
+        if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit()
+        else 0
+    ) or torch.cuda.current_device()
+
+
 def get_cuda_device_string():
     if shared.cmd_opts.device_id is not None:
         return f"cuda:{shared.cmd_opts.device_id}"
@@ -40,6 +57,9 @@ def get_optimal_device_name():
     if has_xpu():
         return xpu_specific.get_xpu_device_string()
 
+    if npu_specific.has_npu:
+        return npu_specific.get_npu_device_string()
+
     return "cpu"
 
 
@@ -67,14 +87,23 @@ def torch_gc():
     if has_xpu():
         xpu_specific.torch_xpu_gc()
 
+    if npu_specific.has_npu:
+        torch_npu_set_device()
+        npu_specific.torch_npu_gc()
+
+
+def torch_npu_set_device():
+    # Work around due to bug in torch_npu, revert me after fixed, @see https://gitee.com/ascend/pytorch/issues/I8KECW?from=project-issue
+    if npu_specific.has_npu:
+        torch.npu.set_device(0)
+
 
 def enable_tf32():
     if torch.cuda.is_available():
 
         # enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't
         # see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407
-        device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device()
-        if torch.cuda.get_device_capability(device_id) == (7, 5) and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16"):
+        if cuda_no_autocast():
             torch.backends.cudnn.benchmark = True
 
         torch.backends.cuda.matmul.allow_tf32 = True
@@ -84,6 +113,10 @@ def enable_tf32():
 errors.run(enable_tf32, "Enabling TF32")
 
 cpu: torch.device = torch.device("cpu")
+fp8: bool = False
+# Force fp16 for all models in inference. No casting during inference.
+# This flag is controlled by "--precision half" command line arg.
+force_fp16: bool = False
 device: torch.device = None
 device_interrogate: torch.device = None
 device_gfpgan: torch.device = None
@@ -92,10 +125,13 @@ device_codeformer: torch.device = None
 dtype: torch.dtype = torch.float16
 dtype_vae: torch.dtype = torch.float16
 dtype_unet: torch.dtype = torch.float16
+dtype_inference: torch.dtype = torch.float16
 unet_needs_upcast = False
 
 
 def cond_cast_unet(input):
+    if force_fp16:
+        return input.to(torch.float16)
     return input.to(dtype_unet) if unet_needs_upcast else input
 
 
@@ -104,15 +140,94 @@ def cond_cast_float(input):
 
 
 nv_rng = None
+patch_module_list = [
+    torch.nn.Linear,
+    torch.nn.Conv2d,
+    torch.nn.MultiheadAttention,
+    torch.nn.GroupNorm,
+    torch.nn.LayerNorm,
+]
+
+
+def manual_cast_forward(target_dtype):
+    def forward_wrapper(self, *args, **kwargs):
+        if any(
+            isinstance(arg, torch.Tensor) and arg.dtype != target_dtype
+            for arg in args
+        ):
+            args = [arg.to(target_dtype) if isinstance(arg, torch.Tensor) else arg for arg in args]
+            kwargs = {k: v.to(target_dtype) if isinstance(v, torch.Tensor) else v for k, v in kwargs.items()}
+
+        org_dtype = target_dtype
+        for param in self.parameters():
+            if param.dtype != target_dtype:
+                org_dtype = param.dtype
+                break
+
+        if org_dtype != target_dtype:
+            self.to(target_dtype)
+        result = self.org_forward(*args, **kwargs)
+        if org_dtype != target_dtype:
+            self.to(org_dtype)
+
+        if target_dtype != dtype_inference:
+            if isinstance(result, tuple):
+                result = tuple(
+                    i.to(dtype_inference)
+                    if isinstance(i, torch.Tensor)
+                    else i
+                    for i in result
+                )
+            elif isinstance(result, torch.Tensor):
+                result = result.to(dtype_inference)
+        return result
+    return forward_wrapper
+
+
+@contextlib.contextmanager
+def manual_cast(target_dtype):
+    applied = False
+    for module_type in patch_module_list:
+        if hasattr(module_type, "org_forward"):
+            continue
+        applied = True
+        org_forward = module_type.forward
+        if module_type == torch.nn.MultiheadAttention:
+            module_type.forward = manual_cast_forward(torch.float32)
+        else:
+            module_type.forward = manual_cast_forward(target_dtype)
+        module_type.org_forward = org_forward
+    try:
+        yield None
+    finally:
+        if applied:
+            for module_type in patch_module_list:
+                if hasattr(module_type, "org_forward"):
+                    module_type.forward = module_type.org_forward
+                    delattr(module_type, "org_forward")
 
 
 def autocast(disable=False):
     if disable:
         return contextlib.nullcontext()
 
-    if dtype == torch.float32 or shared.cmd_opts.precision == "full":
+    if force_fp16:
+        # No casting during inference if force_fp16 is enabled.
+        # All tensor dtype conversion happens before inference.
         return contextlib.nullcontext()
 
+    if fp8 and device==cpu:
+        return torch.autocast("cpu", dtype=torch.bfloat16, enabled=True)
+
+    if fp8 and dtype_inference == torch.float32:
+        return manual_cast(dtype)
+
+    if dtype == torch.float32 or dtype_inference == torch.float32:
+        return contextlib.nullcontext()
+
+    if has_xpu() or has_mps() or cuda_no_autocast():
+        return manual_cast(dtype)
+
     return torch.autocast("cuda")
 
 
@@ -128,22 +243,22 @@ def test_for_nans(x, where):
     if shared.cmd_opts.disable_nan_check:
         return
 
-    if not torch.all(torch.isnan(x)).item():
+    if not torch.isnan(x[(0, ) * len(x.shape)]):
         return
 
     if where == "unet":
-        message = "A tensor with all NaNs was produced in Unet."
+        message = "A tensor with NaNs was produced in Unet."
 
         if not shared.cmd_opts.no_half:
             message += " This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the \"Upcast cross attention layer to float32\" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this."
 
     elif where == "vae":
-        message = "A tensor with all NaNs was produced in VAE."
+        message = "A tensor with NaNs was produced in VAE."
 
         if not shared.cmd_opts.no_half and not shared.cmd_opts.no_half_vae:
             message += " This could be because there's not enough precision to represent the picture. Try adding --no-half-vae commandline argument to fix this."
     else:
-        message = "A tensor with all NaNs was produced."
+        message = "A tensor with NaNs was produced."
 
     message += " Use --disable-nan-check commandline argument to disable this check."
 
@@ -153,8 +268,8 @@ def test_for_nans(x, where):
 @lru_cache
 def first_time_calculation():
     """
-    just do any calculation with pytorch layers - the first time this is done it allocaltes about 700MB of memory and
-    spends about 2.7 seconds doing that, at least wih NVidia.
+    just do any calculation with pytorch layers - the first time this is done it allocates about 700MB of memory and
+    spends about 2.7 seconds doing that, at least with NVidia.
     """
 
     x = torch.zeros((1, 1)).to(device, dtype)
@@ -165,3 +280,16 @@ def first_time_calculation():
     conv2d = torch.nn.Conv2d(1, 1, (3, 3)).to(device, dtype)
     conv2d(x)
 
+
+def force_model_fp16():
+    """
+    ldm and sgm has modules.diffusionmodules.util.GroupNorm32.forward, which
+    force conversion of input to float32. If force_fp16 is enabled, we need to
+    prevent this casting.
+    """
+    assert force_fp16
+    import sgm.modules.diffusionmodules.util as sgm_util
+    import ldm.modules.diffusionmodules.util as ldm_util
+    sgm_util.GroupNorm32 = torch.nn.GroupNorm
+    ldm_util.GroupNorm32 = torch.nn.GroupNorm
+    print("ldm/sgm GroupNorm32 replaced with normal torch.nn.GroupNorm due to `--precision half`.")

modules/errors.py

@@ -107,8 +107,8 @@ def check_versions():
     import torch
     import gradio
 
-    expected_torch_version = "2.0.0"
-    expected_xformers_version = "0.0.20"
+    expected_torch_version = "2.1.2"
+    expected_xformers_version = "0.0.23.post1"
     expected_gradio_version = "3.41.2"
 
     if version.parse(torch.__version__) < version.parse(expected_torch_version):

modules/esrgan_model.py

@@ -1,121 +1,7 @@
-import sys
-
-import numpy as np
-import torch
-from PIL import Image
-
-import modules.esrgan_model_arch as arch
-from modules import modelloader, images, devices
+from modules import modelloader, devices, errors
 from modules.shared import opts
 from modules.upscaler import Upscaler, UpscalerData
-
-
-def mod2normal(state_dict):
-    # this code is copied from https://github.com/victorca25/iNNfer
-    if 'conv_first.weight' in state_dict:
-        crt_net = {}
-        items = list(state_dict)
-
-        crt_net['model.0.weight'] = state_dict['conv_first.weight']
-        crt_net['model.0.bias'] = state_dict['conv_first.bias']
-
-        for k in items.copy():
-            if 'RDB' in k:
-                ori_k = k.replace('RRDB_trunk.', 'model.1.sub.')
-                if '.weight' in k:
-                    ori_k = ori_k.replace('.weight', '.0.weight')
-                elif '.bias' in k:
-                    ori_k = ori_k.replace('.bias', '.0.bias')
-                crt_net[ori_k] = state_dict[k]
-                items.remove(k)
-
-        crt_net['model.1.sub.23.weight'] = state_dict['trunk_conv.weight']
-        crt_net['model.1.sub.23.bias'] = state_dict['trunk_conv.bias']
-        crt_net['model.3.weight'] = state_dict['upconv1.weight']
-        crt_net['model.3.bias'] = state_dict['upconv1.bias']
-        crt_net['model.6.weight'] = state_dict['upconv2.weight']
-        crt_net['model.6.bias'] = state_dict['upconv2.bias']
-        crt_net['model.8.weight'] = state_dict['HRconv.weight']
-        crt_net['model.8.bias'] = state_dict['HRconv.bias']
-        crt_net['model.10.weight'] = state_dict['conv_last.weight']
-        crt_net['model.10.bias'] = state_dict['conv_last.bias']
-        state_dict = crt_net
-    return state_dict
-
-
-def resrgan2normal(state_dict, nb=23):
-    # this code is copied from https://github.com/victorca25/iNNfer
-    if "conv_first.weight" in state_dict and "body.0.rdb1.conv1.weight" in state_dict:
-        re8x = 0
-        crt_net = {}
-        items = list(state_dict)
-
-        crt_net['model.0.weight'] = state_dict['conv_first.weight']
-        crt_net['model.0.bias'] = state_dict['conv_first.bias']
-
-        for k in items.copy():
-            if "rdb" in k:
-                ori_k = k.replace('body.', 'model.1.sub.')
-                ori_k = ori_k.replace('.rdb', '.RDB')
-                if '.weight' in k:
-                    ori_k = ori_k.replace('.weight', '.0.weight')
-                elif '.bias' in k:
-                    ori_k = ori_k.replace('.bias', '.0.bias')
-                crt_net[ori_k] = state_dict[k]
-                items.remove(k)
-
-        crt_net[f'model.1.sub.{nb}.weight'] = state_dict['conv_body.weight']
-        crt_net[f'model.1.sub.{nb}.bias'] = state_dict['conv_body.bias']
-        crt_net['model.3.weight'] = state_dict['conv_up1.weight']
-        crt_net['model.3.bias'] = state_dict['conv_up1.bias']
-        crt_net['model.6.weight'] = state_dict['conv_up2.weight']
-        crt_net['model.6.bias'] = state_dict['conv_up2.bias']
-
-        if 'conv_up3.weight' in state_dict:
-            # modification supporting: https://github.com/ai-forever/Real-ESRGAN/blob/main/RealESRGAN/rrdbnet_arch.py
-            re8x = 3
-            crt_net['model.9.weight'] = state_dict['conv_up3.weight']
-            crt_net['model.9.bias'] = state_dict['conv_up3.bias']
-
-        crt_net[f'model.{8+re8x}.weight'] = state_dict['conv_hr.weight']
-        crt_net[f'model.{8+re8x}.bias'] = state_dict['conv_hr.bias']
-        crt_net[f'model.{10+re8x}.weight'] = state_dict['conv_last.weight']
-        crt_net[f'model.{10+re8x}.bias'] = state_dict['conv_last.bias']
-
-        state_dict = crt_net
-    return state_dict
-
-
-def infer_params(state_dict):
-    # this code is copied from https://github.com/victorca25/iNNfer
-    scale2x = 0
-    scalemin = 6
-    n_uplayer = 0
-    plus = False
-
-    for block in list(state_dict):
-        parts = block.split(".")
-        n_parts = len(parts)
-        if n_parts == 5 and parts[2] == "sub":
-            nb = int(parts[3])
-        elif n_parts == 3:
-            part_num = int(parts[1])
-            if (part_num > scalemin
-                and parts[0] == "model"
-                and parts[2] == "weight"):
-                scale2x += 1
-            if part_num > n_uplayer:
-                n_uplayer = part_num
-                out_nc = state_dict[block].shape[0]
-        if not plus and "conv1x1" in block:
-            plus = True
-
-    nf = state_dict["model.0.weight"].shape[0]
-    in_nc = state_dict["model.0.weight"].shape[1]
-    out_nc = out_nc
-    scale = 2 ** scale2x
-
-    return in_nc, out_nc, nf, nb, plus, scale
+from modules.upscaler_utils import upscale_with_model
 
 
 class UpscalerESRGAN(Upscaler):
@@ -143,12 +29,11 @@ class UpscalerESRGAN(Upscaler):
     def do_upscale(self, img, selected_model):
         try:
             model = self.load_model(selected_model)
-        except Exception as e:
-            print(f"Unable to load ESRGAN model {selected_model}: {e}", file=sys.stderr)
+        except Exception:
+            errors.report(f"Unable to load ESRGAN model {selected_model}", exc_info=True)
             return img
         model.to(devices.device_esrgan)
-        img = esrgan_upscale(model, img)
-        return img
+        return esrgan_upscale(model, img)
 
     def load_model(self, path: str):
         if path.startswith("http"):
@@ -161,69 +46,17 @@ class UpscalerESRGAN(Upscaler):
         else:
             filename = path
 
-        state_dict = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
-
-        if "params_ema" in state_dict:
-            state_dict = state_dict["params_ema"]
-        elif "params" in state_dict:
-            state_dict = state_dict["params"]
-            num_conv = 16 if "realesr-animevideov3" in filename else 32
-            model = arch.SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=num_conv, upscale=4, act_type='prelu')
-            model.load_state_dict(state_dict)
-            model.eval()
-            return model
-
-        if "body.0.rdb1.conv1.weight" in state_dict and "conv_first.weight" in state_dict:
-            nb = 6 if "RealESRGAN_x4plus_anime_6B" in filename else 23
-            state_dict = resrgan2normal(state_dict, nb)
-        elif "conv_first.weight" in state_dict:
-            state_dict = mod2normal(state_dict)
-        elif "model.0.weight" not in state_dict:
-            raise Exception("The file is not a recognized ESRGAN model.")
-
-        in_nc, out_nc, nf, nb, plus, mscale = infer_params(state_dict)
-
-        model = arch.RRDBNet(in_nc=in_nc, out_nc=out_nc, nf=nf, nb=nb, upscale=mscale, plus=plus)
-        model.load_state_dict(state_dict)
-        model.eval()
-
-        return model
-
-
-def upscale_without_tiling(model, img):
-    img = np.array(img)
-    img = img[:, :, ::-1]
-    img = np.ascontiguousarray(np.transpose(img, (2, 0, 1))) / 255
-    img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(devices.device_esrgan)
-    with torch.no_grad():
-        output = model(img)
-    output = output.squeeze().float().cpu().clamp_(0, 1).numpy()
-    output = 255. * np.moveaxis(output, 0, 2)
-    output = output.astype(np.uint8)
-    output = output[:, :, ::-1]
-    return Image.fromarray(output, 'RGB')
+        return modelloader.load_spandrel_model(
+            filename,
+            device=('cpu' if devices.device_esrgan.type == 'mps' else None),
+            expected_architecture='ESRGAN',
+        )
 
 
 def esrgan_upscale(model, img):
-    if opts.ESRGAN_tile == 0:
-        return upscale_without_tiling(model, img)
-
-    grid = images.split_grid(img, opts.ESRGAN_tile, opts.ESRGAN_tile, opts.ESRGAN_tile_overlap)
-    newtiles = []
-    scale_factor = 1
-
-    for y, h, row in grid.tiles:
-        newrow = []
-        for tiledata in row:
-            x, w, tile = tiledata
-
-            output = upscale_without_tiling(model, tile)
-            scale_factor = output.width // tile.width
-
-            newrow.append([x * scale_factor, w * scale_factor, output])
-        newtiles.append([y * scale_factor, h * scale_factor, newrow])
-
-    newgrid = images.Grid(newtiles, grid.tile_w * scale_factor, grid.tile_h * scale_factor, grid.image_w * scale_factor, grid.image_h * scale_factor, grid.overlap * scale_factor)
-    output = images.combine_grid(newgrid)
-    return output
+    return upscale_with_model(
+        model,
+        img,
+        tile_size=opts.ESRGAN_tile,
+        tile_overlap=opts.ESRGAN_tile_overlap,
+    )

modules/esrgan_model_arch.py

@@ -1,465 +0,0 @@
-# this file is adapted from https://github.com/victorca25/iNNfer
-
-from collections import OrderedDict
-import math
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-####################
-# RRDBNet Generator
-####################
-
-class RRDBNet(nn.Module):
-    def __init__(self, in_nc, out_nc, nf, nb, nr=3, gc=32, upscale=4, norm_type=None,
-            act_type='leakyrelu', mode='CNA', upsample_mode='upconv', convtype='Conv2D',
-            finalact=None, gaussian_noise=False, plus=False):
-        super(RRDBNet, self).__init__()
-        n_upscale = int(math.log(upscale, 2))
-        if upscale == 3:
-            n_upscale = 1
-
-        self.resrgan_scale = 0
-        if in_nc % 16 == 0:
-            self.resrgan_scale = 1
-        elif in_nc != 4 and in_nc % 4 == 0:
-            self.resrgan_scale = 2
-
-        fea_conv = conv_block(in_nc, nf, kernel_size=3, norm_type=None, act_type=None, convtype=convtype)
-        rb_blocks = [RRDB(nf, nr, kernel_size=3, gc=32, stride=1, bias=1, pad_type='zero',
-            norm_type=norm_type, act_type=act_type, mode='CNA', convtype=convtype,
-            gaussian_noise=gaussian_noise, plus=plus) for _ in range(nb)]
-        LR_conv = conv_block(nf, nf, kernel_size=3, norm_type=norm_type, act_type=None, mode=mode, convtype=convtype)
-
-        if upsample_mode == 'upconv':
-            upsample_block = upconv_block
-        elif upsample_mode == 'pixelshuffle':
-            upsample_block = pixelshuffle_block
-        else:
-            raise NotImplementedError(f'upsample mode [{upsample_mode}] is not found')
-        if upscale == 3:
-            upsampler = upsample_block(nf, nf, 3, act_type=act_type, convtype=convtype)
-        else:
-            upsampler = [upsample_block(nf, nf, act_type=act_type, convtype=convtype) for _ in range(n_upscale)]
-        HR_conv0 = conv_block(nf, nf, kernel_size=3, norm_type=None, act_type=act_type, convtype=convtype)
-        HR_conv1 = conv_block(nf, out_nc, kernel_size=3, norm_type=None, act_type=None, convtype=convtype)
-
-        outact = act(finalact) if finalact else None
-
-        self.model = sequential(fea_conv, ShortcutBlock(sequential(*rb_blocks, LR_conv)),
-            *upsampler, HR_conv0, HR_conv1, outact)
-
-    def forward(self, x, outm=None):
-        if self.resrgan_scale == 1:
-            feat = pixel_unshuffle(x, scale=4)
-        elif self.resrgan_scale == 2:
-            feat = pixel_unshuffle(x, scale=2)
-        else:
-            feat = x
-
-        return self.model(feat)
-
-
-class RRDB(nn.Module):
-    """
-    Residual in Residual Dense Block
-    (ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks)
-    """
-
-    def __init__(self, nf, nr=3, kernel_size=3, gc=32, stride=1, bias=1, pad_type='zero',
-            norm_type=None, act_type='leakyrelu', mode='CNA', convtype='Conv2D',
-            spectral_norm=False, gaussian_noise=False, plus=False):
-        super(RRDB, self).__init__()
-        # This is for backwards compatibility with existing models
-        if nr == 3:
-            self.RDB1 = ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
-                    norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
-                    gaussian_noise=gaussian_noise, plus=plus)
-            self.RDB2 = ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
-                    norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
-                    gaussian_noise=gaussian_noise, plus=plus)
-            self.RDB3 = ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
-                    norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
-                    gaussian_noise=gaussian_noise, plus=plus)
-        else:
-            RDB_list = [ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
-                                              norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
-                                              gaussian_noise=gaussian_noise, plus=plus) for _ in range(nr)]
-            self.RDBs = nn.Sequential(*RDB_list)
-
-    def forward(self, x):
-        if hasattr(self, 'RDB1'):
-            out = self.RDB1(x)
-            out = self.RDB2(out)
-            out = self.RDB3(out)
-        else:
-            out = self.RDBs(x)
-        return out * 0.2 + x
-
-
-class ResidualDenseBlock_5C(nn.Module):
-    """
-    Residual Dense Block
-    The core module of paper: (Residual Dense Network for Image Super-Resolution, CVPR 18)
-    Modified options that can be used:
-        - "Partial Convolution based Padding" arXiv:1811.11718
-        - "Spectral normalization" arXiv:1802.05957
-        - "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C.
-            {Rakotonirina} and A. {Rasoanaivo}
-    """
-
-    def __init__(self, nf=64, kernel_size=3, gc=32, stride=1, bias=1, pad_type='zero',
-            norm_type=None, act_type='leakyrelu', mode='CNA', convtype='Conv2D',
-            spectral_norm=False, gaussian_noise=False, plus=False):
-        super(ResidualDenseBlock_5C, self).__init__()
-
-        self.noise = GaussianNoise() if gaussian_noise else None
-        self.conv1x1 = conv1x1(nf, gc) if plus else None
-
-        self.conv1 = conv_block(nf, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
-            norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
-            spectral_norm=spectral_norm)
-        self.conv2 = conv_block(nf+gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
-            norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
-            spectral_norm=spectral_norm)
-        self.conv3 = conv_block(nf+2*gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
-            norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
-            spectral_norm=spectral_norm)
-        self.conv4 = conv_block(nf+3*gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
-            norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
-            spectral_norm=spectral_norm)
-        if mode == 'CNA':
-            last_act = None
-        else:
-            last_act = act_type
-        self.conv5 = conv_block(nf+4*gc, nf, 3, stride, bias=bias, pad_type=pad_type,
-            norm_type=norm_type, act_type=last_act, mode=mode, convtype=convtype,
-            spectral_norm=spectral_norm)
-
-    def forward(self, x):
-        x1 = self.conv1(x)
-        x2 = self.conv2(torch.cat((x, x1), 1))
-        if self.conv1x1:
-            x2 = x2 + self.conv1x1(x)
-        x3 = self.conv3(torch.cat((x, x1, x2), 1))
-        x4 = self.conv4(torch.cat((x, x1, x2, x3), 1))
-        if self.conv1x1:
-            x4 = x4 + x2
-        x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
-        if self.noise:
-            return self.noise(x5.mul(0.2) + x)
-        else:
-            return x5 * 0.2 + x
-
-
-####################
-# ESRGANplus
-####################
-
-class GaussianNoise(nn.Module):
-    def __init__(self, sigma=0.1, is_relative_detach=False):
-        super().__init__()
-        self.sigma = sigma
-        self.is_relative_detach = is_relative_detach
-        self.noise = torch.tensor(0, dtype=torch.float)
-
-    def forward(self, x):
-        if self.training and self.sigma != 0:
-            self.noise = self.noise.to(x.device)
-            scale = self.sigma * x.detach() if self.is_relative_detach else self.sigma * x
-            sampled_noise = self.noise.repeat(*x.size()).normal_() * scale
-            x = x + sampled_noise
-        return x
-
-def conv1x1(in_planes, out_planes, stride=1):
-    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
-
-
-####################
-# SRVGGNetCompact
-####################
-
-class SRVGGNetCompact(nn.Module):
-    """A compact VGG-style network structure for super-resolution.
-    This class is copied from https://github.com/xinntao/Real-ESRGAN
-    """
-
-    def __init__(self, num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu'):
-        super(SRVGGNetCompact, self).__init__()
-        self.num_in_ch = num_in_ch
-        self.num_out_ch = num_out_ch
-        self.num_feat = num_feat
-        self.num_conv = num_conv
-        self.upscale = upscale
-        self.act_type = act_type
-
-        self.body = nn.ModuleList()
-        # the first conv
-        self.body.append(nn.Conv2d(num_in_ch, num_feat, 3, 1, 1))
-        # the first activation
-        if act_type == 'relu':
-            activation = nn.ReLU(inplace=True)
-        elif act_type == 'prelu':
-            activation = nn.PReLU(num_parameters=num_feat)
-        elif act_type == 'leakyrelu':
-            activation = nn.LeakyReLU(negative_slope=0.1, inplace=True)
-        self.body.append(activation)
-
-        # the body structure
-        for _ in range(num_conv):
-            self.body.append(nn.Conv2d(num_feat, num_feat, 3, 1, 1))
-            # activation
-            if act_type == 'relu':
-                activation = nn.ReLU(inplace=True)
-            elif act_type == 'prelu':
-                activation = nn.PReLU(num_parameters=num_feat)
-            elif act_type == 'leakyrelu':
-                activation = nn.LeakyReLU(negative_slope=0.1, inplace=True)
-            self.body.append(activation)
-
-        # the last conv
-        self.body.append(nn.Conv2d(num_feat, num_out_ch * upscale * upscale, 3, 1, 1))
-        # upsample
-        self.upsampler = nn.PixelShuffle(upscale)
-
-    def forward(self, x):
-        out = x
-        for i in range(0, len(self.body)):
-            out = self.body[i](out)
-
-        out = self.upsampler(out)
-        # add the nearest upsampled image, so that the network learns the residual
-        base = F.interpolate(x, scale_factor=self.upscale, mode='nearest')
-        out += base
-        return out
-
-
-####################
-# Upsampler
-####################
-
-class Upsample(nn.Module):
-    r"""Upsamples a given multi-channel 1D (temporal), 2D (spatial) or 3D (volumetric) data.
-    The input data is assumed to be of the form
-    `minibatch x channels x [optional depth] x [optional height] x width`.
-    """
-
-    def __init__(self, size=None, scale_factor=None, mode="nearest", align_corners=None):
-        super(Upsample, self).__init__()
-        if isinstance(scale_factor, tuple):
-            self.scale_factor = tuple(float(factor) for factor in scale_factor)
-        else:
-            self.scale_factor = float(scale_factor) if scale_factor else None
-        self.mode = mode
-        self.size = size
-        self.align_corners = align_corners
-
-    def forward(self, x):
-        return nn.functional.interpolate(x, size=self.size, scale_factor=self.scale_factor, mode=self.mode, align_corners=self.align_corners)
-
-    def extra_repr(self):
-        if self.scale_factor is not None:
-            info = f'scale_factor={self.scale_factor}'
-        else:
-            info = f'size={self.size}'
-        info += f', mode={self.mode}'
-        return info
-
-
-def pixel_unshuffle(x, scale):
-    """ Pixel unshuffle.
-    Args:
-        x (Tensor): Input feature with shape (b, c, hh, hw).
-        scale (int): Downsample ratio.
-    Returns:
-        Tensor: the pixel unshuffled feature.
-    """
-    b, c, hh, hw = x.size()
-    out_channel = c * (scale**2)
-    assert hh % scale == 0 and hw % scale == 0
-    h = hh // scale
-    w = hw // scale
-    x_view = x.view(b, c, h, scale, w, scale)
-    return x_view.permute(0, 1, 3, 5, 2, 4).reshape(b, out_channel, h, w)
-
-
-def pixelshuffle_block(in_nc, out_nc, upscale_factor=2, kernel_size=3, stride=1, bias=True,
-                        pad_type='zero', norm_type=None, act_type='relu', convtype='Conv2D'):
-    """
-    Pixel shuffle layer
-    (Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional
-    Neural Network, CVPR17)
-    """
-    conv = conv_block(in_nc, out_nc * (upscale_factor ** 2), kernel_size, stride, bias=bias,
-                        pad_type=pad_type, norm_type=None, act_type=None, convtype=convtype)
-    pixel_shuffle = nn.PixelShuffle(upscale_factor)
-
-    n = norm(norm_type, out_nc) if norm_type else None
-    a = act(act_type) if act_type else None
-    return sequential(conv, pixel_shuffle, n, a)
-
-
-def upconv_block(in_nc, out_nc, upscale_factor=2, kernel_size=3, stride=1, bias=True,
-                pad_type='zero', norm_type=None, act_type='relu', mode='nearest', convtype='Conv2D'):
-    """ Upconv layer """
-    upscale_factor = (1, upscale_factor, upscale_factor) if convtype == 'Conv3D' else upscale_factor
-    upsample = Upsample(scale_factor=upscale_factor, mode=mode)
-    conv = conv_block(in_nc, out_nc, kernel_size, stride, bias=bias,
-                        pad_type=pad_type, norm_type=norm_type, act_type=act_type, convtype=convtype)
-    return sequential(upsample, conv)
-
-
-
-
-
-
-
-
-####################
-# Basic blocks
-####################
-
-
-def make_layer(basic_block, num_basic_block, **kwarg):
-    """Make layers by stacking the same blocks.
-    Args:
-        basic_block (nn.module): nn.module class for basic block. (block)
-        num_basic_block (int): number of blocks. (n_layers)
-    Returns:
-        nn.Sequential: Stacked blocks in nn.Sequential.
-    """
-    layers = []
-    for _ in range(num_basic_block):
-        layers.append(basic_block(**kwarg))
-    return nn.Sequential(*layers)
-
-
-def act(act_type, inplace=True, neg_slope=0.2, n_prelu=1, beta=1.0):
-    """ activation helper """
-    act_type = act_type.lower()
-    if act_type == 'relu':
-        layer = nn.ReLU(inplace)
-    elif act_type in ('leakyrelu', 'lrelu'):
-        layer = nn.LeakyReLU(neg_slope, inplace)
-    elif act_type == 'prelu':
-        layer = nn.PReLU(num_parameters=n_prelu, init=neg_slope)
-    elif act_type == 'tanh':  # [-1, 1] range output
-        layer = nn.Tanh()
-    elif act_type == 'sigmoid':  # [0, 1] range output
-        layer = nn.Sigmoid()
-    else:
-        raise NotImplementedError(f'activation layer [{act_type}] is not found')
-    return layer
-
-
-class Identity(nn.Module):
-    def __init__(self, *kwargs):
-        super(Identity, self).__init__()
-
-    def forward(self, x, *kwargs):
-        return x
-
-
-def norm(norm_type, nc):
-    """ Return a normalization layer """
-    norm_type = norm_type.lower()
-    if norm_type == 'batch':
-        layer = nn.BatchNorm2d(nc, affine=True)
-    elif norm_type == 'instance':
-        layer = nn.InstanceNorm2d(nc, affine=False)
-    elif norm_type == 'none':
-        def norm_layer(x): return Identity()
-    else:
-        raise NotImplementedError(f'normalization layer [{norm_type}] is not found')
-    return layer
-
-
-def pad(pad_type, padding):
-    """ padding layer helper """
-    pad_type = pad_type.lower()
-    if padding == 0:
-        return None
-    if pad_type == 'reflect':
-        layer = nn.ReflectionPad2d(padding)
-    elif pad_type == 'replicate':
-        layer = nn.ReplicationPad2d(padding)
-    elif pad_type == 'zero':
-        layer = nn.ZeroPad2d(padding)
-    else:
-        raise NotImplementedError(f'padding layer [{pad_type}] is not implemented')
-    return layer
-
-
-def get_valid_padding(kernel_size, dilation):
-    kernel_size = kernel_size + (kernel_size - 1) * (dilation - 1)
-    padding = (kernel_size - 1) // 2
-    return padding
-
-
-class ShortcutBlock(nn.Module):
-    """ Elementwise sum the output of a submodule to its input """
-    def __init__(self, submodule):
-        super(ShortcutBlock, self).__init__()
-        self.sub = submodule
-
-    def forward(self, x):
-        output = x + self.sub(x)
-        return output
-
-    def __repr__(self):
-        return 'Identity + \n|' + self.sub.__repr__().replace('\n', '\n|')
-
-
-def sequential(*args):
-    """ Flatten Sequential. It unwraps nn.Sequential. """
-    if len(args) == 1:
-        if isinstance(args[0], OrderedDict):
-            raise NotImplementedError('sequential does not support OrderedDict input.')
-        return args[0]  # No sequential is needed.
-    modules = []
-    for module in args:
-        if isinstance(module, nn.Sequential):
-            for submodule in module.children():
-                modules.append(submodule)
-        elif isinstance(module, nn.Module):
-            modules.append(module)
-    return nn.Sequential(*modules)
-
-
-def conv_block(in_nc, out_nc, kernel_size, stride=1, dilation=1, groups=1, bias=True,
-               pad_type='zero', norm_type=None, act_type='relu', mode='CNA', convtype='Conv2D',
-               spectral_norm=False):
-    """ Conv layer with padding, normalization, activation """
-    assert mode in ['CNA', 'NAC', 'CNAC'], f'Wrong conv mode [{mode}]'
-    padding = get_valid_padding(kernel_size, dilation)
-    p = pad(pad_type, padding) if pad_type and pad_type != 'zero' else None
-    padding = padding if pad_type == 'zero' else 0
-
-    if convtype=='PartialConv2D':
-        from torchvision.ops import PartialConv2d  # this is definitely not going to work, but PartialConv2d doesn't work anyway and this shuts up static analyzer
-        c = PartialConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
-               dilation=dilation, bias=bias, groups=groups)
-    elif convtype=='DeformConv2D':
-        from torchvision.ops import DeformConv2d  # not tested
-        c = DeformConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
-               dilation=dilation, bias=bias, groups=groups)
-    elif convtype=='Conv3D':
-        c = nn.Conv3d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
-                dilation=dilation, bias=bias, groups=groups)
-    else:
-        c = nn.Conv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
-                dilation=dilation, bias=bias, groups=groups)
-
-    if spectral_norm:
-        c = nn.utils.spectral_norm(c)
-
-    a = act(act_type) if act_type else None
-    if 'CNA' in mode:
-        n = norm(norm_type, out_nc) if norm_type else None
-        return sequential(p, c, n, a)
-    elif mode == 'NAC':
-        if norm_type is None and act_type is not None:
-            a = act(act_type, inplace=False)
-        n = norm(norm_type, in_nc) if norm_type else None
-        return sequential(n, a, p, c)

modules/extensions.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import configparser
+import dataclasses
 import os
 import threading
 import re
@@ -9,6 +10,10 @@ from modules import shared, errors, cache, scripts
 from modules.gitpython_hack import Repo
 from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path  # noqa: F401
 
+extensions: list[Extension] = []
+extension_paths: dict[str, Extension] = {}
+loaded_extensions: dict[str, Exception] = {}
+
 
 os.makedirs(extensions_dir, exist_ok=True)
 
@@ -22,6 +27,13 @@ def active():
         return [x for x in extensions if x.enabled]
 
 
+@dataclasses.dataclass
+class CallbackOrderInfo:
+    name: str
+    before: list
+    after: list
+
+
 class ExtensionMetadata:
     filename = "metadata.ini"
     config: configparser.ConfigParser
@@ -32,16 +44,17 @@ class ExtensionMetadata:
         self.config = configparser.ConfigParser()
 
         filepath = os.path.join(path, self.filename)
-        if os.path.isfile(filepath):
-            try:
-                self.config.read(filepath)
-            except Exception:
-                errors.report(f"Error reading {self.filename} for extension {canonical_name}.", exc_info=True)
+        # `self.config.read()` will quietly swallow OSErrors (which FileNotFoundError is),
+        # so no need to check whether the file exists beforehand.
+        try:
+            self.config.read(filepath)
+        except Exception:
+            errors.report(f"Error reading {self.filename} for extension {canonical_name}.", exc_info=True)
 
         self.canonical_name = self.config.get("Extension", "Name", fallback=canonical_name)
         self.canonical_name = canonical_name.lower().strip()
 
-        self.requires = self.get_script_requirements("Requires", "Extension")
+        self.requires = None
 
     def get_script_requirements(self, field, section, extra_section=None):
         """reads a list of requirements from the config; field is the name of the field in the ini file,
@@ -53,7 +66,15 @@ class ExtensionMetadata:
         if extra_section:
             x = x + ', ' + self.config.get(extra_section, field, fallback='')
 
-        return self.parse_list(x.lower())
+        listed_requirements = self.parse_list(x.lower())
+        res = []
+
+        for requirement in listed_requirements:
+            loaded_requirements = (x for x in requirement.split("|") if x in loaded_extensions)
+            relevant_requirement = next(loaded_requirements, requirement)
+            res.append(relevant_requirement)
+
+        return res
 
     def parse_list(self, text):
         """converts a line from config ("ext1 ext2, ext3  ") into a python list (["ext1", "ext2", "ext3"])"""
@@ -64,6 +85,22 @@ class ExtensionMetadata:
         # both "," and " " are accepted as separator
         return [x for x in re.split(r"[,\s]+", text.strip()) if x]
 
+    def list_callback_order_instructions(self):
+        for section in self.config.sections():
+            if not section.startswith("callbacks/"):
+                continue
+
+            callback_name = section[10:]
+
+            if not callback_name.startswith(self.canonical_name):
+                errors.report(f"Callback order section for extension {self.canonical_name} is referencing the wrong extension: {section}")
+                continue
+
+            before = self.parse_list(self.config.get(section, 'Before', fallback=''))
+            after = self.parse_list(self.config.get(section, 'After', fallback=''))
+
+            yield CallbackOrderInfo(callback_name, before, after)
+
 
 class Extension:
     lock = threading.Lock()
@@ -154,14 +191,17 @@ class Extension:
 
     def check_updates(self):
         repo = Repo(self.path)
+        branch_name = f'{repo.remote().name}/{self.branch}'
         for fetch in repo.remote().fetch(dry_run=True):
+            if self.branch and fetch.name != branch_name:
+                continue
             if fetch.flags != fetch.HEAD_UPTODATE:
                 self.can_update = True
                 self.status = "new commits"
                 return
 
         try:
-            origin = repo.rev_parse('origin')
+            origin = repo.rev_parse(branch_name)
             if repo.head.commit != origin:
                 self.can_update = True
                 self.status = "behind HEAD"
@@ -174,8 +214,10 @@ class Extension:
         self.can_update = False
         self.status = "latest"
 
-    def fetch_and_reset_hard(self, commit='origin'):
+    def fetch_and_reset_hard(self, commit=None):
         repo = Repo(self.path)
+        if commit is None:
+            commit = f'{repo.remote().name}/{self.branch}'
         # Fix: `error: Your local changes to the following files would be overwritten by merge`,
         # because WSL2 Docker set 755 file permissions instead of 644, this results to the error.
         repo.git.fetch(all=True)
@@ -185,6 +227,8 @@ class Extension:
 
 def list_extensions():
     extensions.clear()
+    extension_paths.clear()
+    loaded_extensions.clear()
 
     if shared.cmd_opts.disable_all_extensions:
         print("*** \"--disable-all-extensions\" arg was used, will not load any extensions ***")
@@ -195,7 +239,6 @@ def list_extensions():
     elif shared.opts.disable_all_extensions == "extra":
         print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
 
-    loaded_extensions = {}
 
     # scan through extensions directory and load metadata
     for dirname in [extensions_builtin_dir, extensions_dir]:
@@ -219,19 +262,38 @@ def list_extensions():
             is_builtin = dirname == extensions_builtin_dir
             extension = Extension(name=extension_dirname, path=path, enabled=extension_dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin, metadata=metadata)
             extensions.append(extension)
+            extension_paths[extension.path] = extension
             loaded_extensions[canonical_name] = extension
 
+    for extension in extensions:
+        extension.metadata.requires = extension.metadata.get_script_requirements("Requires", "Extension")
+
     # check for requirements
     for extension in extensions:
+        if not extension.enabled:
+            continue
+
         for req in extension.metadata.requires:
             required_extension = loaded_extensions.get(req)
             if required_extension is None:
                 errors.report(f'Extension "{extension.name}" requires "{req}" which is not installed.', exc_info=False)
                 continue
 
-            if not extension.enabled:
+            if not required_extension.enabled:
                 errors.report(f'Extension "{extension.name}" requires "{required_extension.name}" which is disabled.', exc_info=False)
                 continue
 
 
-extensions: list[Extension] = []
+def find_extension(filename):
+    parentdir = os.path.dirname(os.path.realpath(filename))
+
+    while parentdir != filename:
+        extension = extension_paths.get(parentdir)
+        if extension is not None:
+            return extension
+
+        filename = parentdir
+        parentdir = os.path.dirname(filename)
+
+    return None
+

modules/extra_networks.py

@@ -60,7 +60,7 @@ class ExtraNetwork:
         Where name matches the name of this ExtraNetwork object, and arg1:arg2:arg3 are any natural number of text arguments
         separated by colon.
 
-        Even if the user does not mention this ExtraNetwork in his prompt, the call will stil be made, with empty params_list -
+        Even if the user does not mention this ExtraNetwork in his prompt, the call will still be made, with empty params_list -
         in this case, all effects of this extra networks should be disabled.
 
         Can be called multiple times before deactivate() - each new call should override the previous call completely.
@@ -206,7 +206,7 @@ def parse_prompts(prompts):
     return res, extra_data
 
 
-def get_user_metadata(filename):
+def get_user_metadata(filename, lister=None):
     if filename is None:
         return {}
 
@@ -215,7 +215,8 @@ def get_user_metadata(filename):
 
     metadata = {}
     try:
-        if os.path.isfile(metadata_filename):
+        exists = lister.exists(metadata_filename) if lister else os.path.exists(metadata_filename)
+        if exists:
             with open(metadata_filename, "r", encoding="utf8") as file:
                 metadata = json.load(file)
     except Exception as e:

modules/face_restoration_utils.py

@@ -0,0 +1,180 @@
+from __future__ import annotations
+
+import logging
+import os
+from functools import cached_property
+from typing import TYPE_CHECKING, Callable
+
+import cv2
+import numpy as np
+import torch
+
+from modules import devices, errors, face_restoration, shared
+
+if TYPE_CHECKING:
+    from facexlib.utils.face_restoration_helper import FaceRestoreHelper
+
+logger = logging.getLogger(__name__)
+
+
+def bgr_image_to_rgb_tensor(img: np.ndarray) -> torch.Tensor:
+    """Convert a BGR NumPy image in [0..1] range to a PyTorch RGB float32 tensor."""
+    assert img.shape[2] == 3, "image must be RGB"
+    if img.dtype == "float64":
+        img = img.astype("float32")
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    return torch.from_numpy(img.transpose(2, 0, 1)).float()
+
+
+def rgb_tensor_to_bgr_image(tensor: torch.Tensor, *, min_max=(0.0, 1.0)) -> np.ndarray:
+    """
+    Convert a PyTorch RGB tensor in range `min_max` to a BGR NumPy image in [0..1] range.
+    """
+    tensor = tensor.squeeze(0).float().detach().cpu().clamp_(*min_max)
+    tensor = (tensor - min_max[0]) / (min_max[1] - min_max[0])
+    assert tensor.dim() == 3, "tensor must be RGB"
+    img_np = tensor.numpy().transpose(1, 2, 0)
+    if img_np.shape[2] == 1:  # gray image, no RGB/BGR required
+        return np.squeeze(img_np, axis=2)
+    return cv2.cvtColor(img_np, cv2.COLOR_BGR2RGB)
+
+
+def create_face_helper(device) -> FaceRestoreHelper:
+    from facexlib.detection import retinaface
+    from facexlib.utils.face_restoration_helper import FaceRestoreHelper
+    if hasattr(retinaface, 'device'):
+        retinaface.device = device
+    return FaceRestoreHelper(
+        upscale_factor=1,
+        face_size=512,
+        crop_ratio=(1, 1),
+        det_model='retinaface_resnet50',
+        save_ext='png',
+        use_parse=True,
+        device=device,
+    )
+
+
+def restore_with_face_helper(
+    np_image: np.ndarray,
+    face_helper: FaceRestoreHelper,
+    restore_face: Callable[[torch.Tensor], torch.Tensor],
+) -> np.ndarray:
+    """
+    Find faces in the image using face_helper, restore them using restore_face, and paste them back into the image.
+
+    `restore_face` should take a cropped face image and return a restored face image.
+    """
+    from torchvision.transforms.functional import normalize
+    np_image = np_image[:, :, ::-1]
+    original_resolution = np_image.shape[0:2]
+
+    try:
+        logger.debug("Detecting faces...")
+        face_helper.clean_all()
+        face_helper.read_image(np_image)
+        face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5)
+        face_helper.align_warp_face()
+        logger.debug("Found %d faces, restoring", len(face_helper.cropped_faces))
+        for cropped_face in face_helper.cropped_faces:
+            cropped_face_t = bgr_image_to_rgb_tensor(cropped_face / 255.0)
+            normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
+            cropped_face_t = cropped_face_t.unsqueeze(0).to(devices.device_codeformer)
+
+            try:
+                with torch.no_grad():
+                    cropped_face_t = restore_face(cropped_face_t)
+                devices.torch_gc()
+            except Exception:
+                errors.report('Failed face-restoration inference', exc_info=True)
+
+            restored_face = rgb_tensor_to_bgr_image(cropped_face_t, min_max=(-1, 1))
+            restored_face = (restored_face * 255.0).astype('uint8')
+            face_helper.add_restored_face(restored_face)
+
+        logger.debug("Merging restored faces into image")
+        face_helper.get_inverse_affine(None)
+        img = face_helper.paste_faces_to_input_image()
+        img = img[:, :, ::-1]
+        if original_resolution != img.shape[0:2]:
+            img = cv2.resize(
+                img,
+                (0, 0),
+                fx=original_resolution[1] / img.shape[1],
+                fy=original_resolution[0] / img.shape[0],
+                interpolation=cv2.INTER_LINEAR,
+            )
+        logger.debug("Face restoration complete")
+    finally:
+        face_helper.clean_all()
+    return img
+
+
+class CommonFaceRestoration(face_restoration.FaceRestoration):
+    net: torch.Module | None
+    model_url: str
+    model_download_name: str
+
+    def __init__(self, model_path: str):
+        super().__init__()
+        self.net = None
+        self.model_path = model_path
+        os.makedirs(model_path, exist_ok=True)
+
+    @cached_property
+    def face_helper(self) -> FaceRestoreHelper:
+        return create_face_helper(self.get_device())
+
+    def send_model_to(self, device):
+        if self.net:
+            logger.debug("Sending %s to %s", self.net, device)
+            self.net.to(device)
+        if self.face_helper:
+            logger.debug("Sending face helper to %s", device)
+            self.face_helper.face_det.to(device)
+            self.face_helper.face_parse.to(device)
+
+    def get_device(self):
+        raise NotImplementedError("get_device must be implemented by subclasses")
+
+    def load_net(self) -> torch.Module:
+        raise NotImplementedError("load_net must be implemented by subclasses")
+
+    def restore_with_helper(
+        self,
+        np_image: np.ndarray,
+        restore_face: Callable[[torch.Tensor], torch.Tensor],
+    ) -> np.ndarray:
+        try:
+            if self.net is None:
+                self.net = self.load_net()
+        except Exception:
+            logger.warning("Unable to load face-restoration model", exc_info=True)
+            return np_image
+
+        try:
+            self.send_model_to(self.get_device())
+            return restore_with_face_helper(np_image, self.face_helper, restore_face)
+        finally:
+            if shared.opts.face_restoration_unload:
+                self.send_model_to(devices.cpu)
+
+
+def patch_facexlib(dirname: str) -> None:
+    import facexlib.detection
+    import facexlib.parsing
+
+    det_facex_load_file_from_url = facexlib.detection.load_file_from_url
+    par_facex_load_file_from_url = facexlib.parsing.load_file_from_url
+
+    def update_kwargs(kwargs):
+        return dict(kwargs, save_dir=dirname, model_dir=None)
+
+    def facex_load_file_from_url(**kwargs):
+        return det_facex_load_file_from_url(**update_kwargs(kwargs))
+
+    def facex_load_file_from_url2(**kwargs):
+        return par_facex_load_file_from_url(**update_kwargs(kwargs))
+
+    facexlib.detection.load_file_from_url = facex_load_file_from_url
+    facexlib.parsing.load_file_from_url = facex_load_file_from_url2

modules/gfpgan_model.py

@@ -1,125 +1,69 @@
+from __future__ import annotations
+
+import logging
 import os
 
-import facexlib
-import gfpgan
+import torch
 
-import modules.face_restoration
-from modules import paths, shared, devices, modelloader, errors
+from modules import (
+    devices,
+    errors,
+    face_restoration,
+    face_restoration_utils,
+    modelloader,
+    shared,
+)
 
-model_dir = "GFPGAN"
-user_path = None
-model_path = os.path.join(paths.models_path, model_dir)
-model_file_path = None
+logger = logging.getLogger(__name__)
 model_url = "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth"
-have_gfpgan = False
-loaded_gfpgan_model = None
+model_download_name = "GFPGANv1.4.pth"
+gfpgan_face_restorer: face_restoration.FaceRestoration | None = None
 
 
-def gfpgann():
-    global loaded_gfpgan_model
-    global model_path
-    global model_file_path
-    if loaded_gfpgan_model is not None:
-        loaded_gfpgan_model.gfpgan.to(devices.device_gfpgan)
-        return loaded_gfpgan_model
+class FaceRestorerGFPGAN(face_restoration_utils.CommonFaceRestoration):
+    def name(self):
+        return "GFPGAN"
 
-    if gfpgan_constructor is None:
-        return None
+    def get_device(self):
+        return devices.device_gfpgan
 
-    models = modelloader.load_models(model_path, model_url, user_path, ext_filter=['.pth'])
+    def load_net(self) -> torch.Module:
+        for model_path in modelloader.load_models(
+            model_path=self.model_path,
+            model_url=model_url,
+            command_path=self.model_path,
+            download_name=model_download_name,
+            ext_filter=['.pth'],
+        ):
+            if 'GFPGAN' in os.path.basename(model_path):
+                return modelloader.load_spandrel_model(
+                    model_path,
+                    device=self.get_device(),
+                    expected_architecture='GFPGAN',
+                ).model
+        raise ValueError("No GFPGAN model found")
 
-    if len(models) == 1 and models[0].startswith("http"):
-        model_file = models[0]
-    elif len(models) != 0:
-        gfp_models = []
-        for item in models:
-            if 'GFPGAN' in os.path.basename(item):
-                gfp_models.append(item)
-        latest_file = max(gfp_models, key=os.path.getctime)
-        model_file = latest_file
-    else:
-        print("Unable to load gfpgan model!")
-        return None
+    def restore(self, np_image):
+        def restore_face(cropped_face_t):
+            assert self.net is not None
+            return self.net(cropped_face_t, return_rgb=False)[0]
 
-    if hasattr(facexlib.detection.retinaface, 'device'):
-        facexlib.detection.retinaface.device = devices.device_gfpgan
-    model_file_path = model_file
-    model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=devices.device_gfpgan)
-    loaded_gfpgan_model = model
-
-    return model
-
-
-def send_model_to(model, device):
-    model.gfpgan.to(device)
-    model.face_helper.face_det.to(device)
-    model.face_helper.face_parse.to(device)
+        return self.restore_with_helper(np_image, restore_face)
 
 
 def gfpgan_fix_faces(np_image):
-    model = gfpgann()
-    if model is None:
-        return np_image
-
-    send_model_to(model, devices.device_gfpgan)
-
-    np_image_bgr = np_image[:, :, ::-1]
-    cropped_faces, restored_faces, gfpgan_output_bgr = model.enhance(np_image_bgr, has_aligned=False, only_center_face=False, paste_back=True)
-    np_image = gfpgan_output_bgr[:, :, ::-1]
-
-    model.face_helper.clean_all()
-
-    if shared.opts.face_restoration_unload:
-        send_model_to(model, devices.cpu)
-
+    if gfpgan_face_restorer:
+        return gfpgan_face_restorer.restore(np_image)
+    logger.warning("GFPGAN face restorer not set up")
     return np_image
 
 
-gfpgan_constructor = None
+def setup_model(dirname: str) -> None:
+    global gfpgan_face_restorer
 
-
-def setup_model(dirname):
     try:
-        os.makedirs(model_path, exist_ok=True)
-        from gfpgan import GFPGANer
-        from facexlib import detection, parsing  # noqa: F401
-        global user_path
-        global have_gfpgan
-        global gfpgan_constructor
-        global model_file_path
-
-        facexlib_path = model_path
-
-        if dirname is not None:
-            facexlib_path = dirname
-
-        load_file_from_url_orig = gfpgan.utils.load_file_from_url
-        facex_load_file_from_url_orig = facexlib.detection.load_file_from_url
-        facex_load_file_from_url_orig2 = facexlib.parsing.load_file_from_url
-
-        def my_load_file_from_url(**kwargs):
-            return load_file_from_url_orig(**dict(kwargs, model_dir=model_file_path))
-
-        def facex_load_file_from_url(**kwargs):
-            return facex_load_file_from_url_orig(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
-
-        def facex_load_file_from_url2(**kwargs):
-            return facex_load_file_from_url_orig2(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
-
-        gfpgan.utils.load_file_from_url = my_load_file_from_url
-        facexlib.detection.load_file_from_url = facex_load_file_from_url
-        facexlib.parsing.load_file_from_url = facex_load_file_from_url2
-        user_path = dirname
-        have_gfpgan = True
-        gfpgan_constructor = GFPGANer
-
-        class FaceRestorerGFPGAN(modules.face_restoration.FaceRestoration):
-            def name(self):
-                return "GFPGAN"
-
-            def restore(self, np_image):
-                return gfpgan_fix_faces(np_image)
-
-        shared.face_restorers.append(FaceRestorerGFPGAN())
+        face_restoration_utils.patch_facexlib(dirname)
+        gfpgan_face_restorer = FaceRestorerGFPGAN(model_path=dirname)
+        shared.face_restorers.append(gfpgan_face_restorer)
     except Exception:
         errors.report("Error setting up GFPGAN", exc_info=True)

modules/hashes.py

@@ -21,7 +21,10 @@ def calculate_sha256(filename):
 
 def sha256_from_cache(filename, title, use_addnet_hash=False):
     hashes = cache("hashes-addnet") if use_addnet_hash else cache("hashes")
-    ondisk_mtime = os.path.getmtime(filename)
+    try:
+        ondisk_mtime = os.path.getmtime(filename)
+    except FileNotFoundError:
+        return None
 
     if title not in hashes:
         return None

modules/hat_model.py

@@ -0,0 +1,43 @@
+import os
+import sys
+
+from modules import modelloader, devices
+from modules.shared import opts
+from modules.upscaler import Upscaler, UpscalerData
+from modules.upscaler_utils import upscale_with_model
+
+
+class UpscalerHAT(Upscaler):
+    def __init__(self, dirname):
+        self.name = "HAT"
+        self.scalers = []
+        self.user_path = dirname
+        super().__init__()
+        for file in self.find_models(ext_filter=[".pt", ".pth"]):
+            name = modelloader.friendly_name(file)
+            scale = 4  # TODO: scale might not be 4, but we can't know without loading the model
+            scaler_data = UpscalerData(name, file, upscaler=self, scale=scale)
+            self.scalers.append(scaler_data)
+
+    def do_upscale(self, img, selected_model):
+        try:
+            model = self.load_model(selected_model)
+        except Exception as e:
+            print(f"Unable to load HAT model {selected_model}: {e}", file=sys.stderr)
+            return img
+        model.to(devices.device_esrgan)  # TODO: should probably be device_hat
+        return upscale_with_model(
+            model,
+            img,
+            tile_size=opts.ESRGAN_tile,  # TODO: should probably be HAT_tile
+            tile_overlap=opts.ESRGAN_tile_overlap,  # TODO: should probably be HAT_tile_overlap
+        )
+
+    def load_model(self, path: str):
+        if not os.path.isfile(path):
+            raise FileNotFoundError(f"Model file {path} not found")
+        return modelloader.load_spandrel_model(
+            path,
+            device=devices.device_esrgan,  # TODO: should probably be device_hat
+            expected_architecture='HAT',
+        )

modules/hypernetworks/hypernetwork.py

@@ -11,7 +11,7 @@ import tqdm
 from einops import rearrange, repeat
 from ldm.util import default
 from modules import devices, sd_models, shared, sd_samplers, hashes, sd_hijack_checkpoint, errors
-from modules.textual_inversion import textual_inversion, logging
+from modules.textual_inversion import textual_inversion, saving_settings
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 from torch import einsum
 from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_
@@ -95,6 +95,7 @@ class HypernetworkModule(torch.nn.Module):
                         zeros_(b)
                     else:
                         raise KeyError(f"Key {weight_init} is not defined as initialization!")
+        devices.torch_npu_set_device()
         self.to(devices.device)
 
     def fix_old_state_dict(self, state_dict):
@@ -532,7 +533,7 @@ def train_hypernetwork(id_task, hypernetwork_name: str, learn_rate: float, batch
             model_name=checkpoint.model_name, model_hash=checkpoint.shorthash, num_of_dataset_images=len(ds),
             **{field: getattr(hypernetwork, field) for field in ['layer_structure', 'activation_func', 'weight_init', 'add_layer_norm', 'use_dropout', ]}
         )
-        logging.save_settings_to_file(log_directory, {**saved_params, **locals()})
+        saving_settings.save_settings_to_file(log_directory, {**saved_params, **locals()})
 
     latent_sampling_method = ds.latent_sampling_method
 

modules/images.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import datetime
-
+import functools
 import pytz
 import io
 import math
@@ -12,7 +12,9 @@ import re
 import numpy as np
 import piexif
 import piexif.helper
-from PIL import Image, ImageFont, ImageDraw, ImageColor, PngImagePlugin
+from PIL import Image, ImageFont, ImageDraw, ImageColor, PngImagePlugin, ImageOps
+# pillow_avif needs to be imported somewhere in code for it to work
+import pillow_avif # noqa: F401
 import string
 import json
 import hashlib
@@ -52,21 +54,29 @@ def image_grid(imgs, batch_size=1, rows=None):
     params = script_callbacks.ImageGridLoopParams(imgs, cols, rows)
     script_callbacks.image_grid_callback(params)
 
-    w, h = imgs[0].size
-    grid = Image.new('RGB', size=(params.cols * w, params.rows * h), color='black')
+    w, h = map(max, zip(*(img.size for img in imgs)))
+    grid_background_color = ImageColor.getcolor(opts.grid_background_color, 'RGB')
+    grid = Image.new('RGB', size=(params.cols * w, params.rows * h), color=grid_background_color)
 
     for i, img in enumerate(params.imgs):
-        grid.paste(img, box=(i % params.cols * w, i // params.cols * h))
+        img_w, img_h = img.size
+        w_offset, h_offset = 0 if img_w == w else (w - img_w) // 2, 0 if img_h == h else (h - img_h) // 2
+        grid.paste(img, box=(i % params.cols * w + w_offset, i // params.cols * h + h_offset))
 
     return grid
 
 
-Grid = namedtuple("Grid", ["tiles", "tile_w", "tile_h", "image_w", "image_h", "overlap"])
+class Grid(namedtuple("_Grid", ["tiles", "tile_w", "tile_h", "image_w", "image_h", "overlap"])):
+    @property
+    def tile_count(self) -> int:
+        """
+        The total number of tiles in the grid.
+        """
+        return sum(len(row[2]) for row in self.tiles)
 
 
-def split_grid(image, tile_w=512, tile_h=512, overlap=64):
-    w = image.width
-    h = image.height
+def split_grid(image: Image.Image, tile_w: int = 512, tile_h: int = 512, overlap: int = 64) -> Grid:
+    w, h = image.size
 
     non_overlap_width = tile_w - overlap
     non_overlap_height = tile_h - overlap
@@ -316,13 +326,16 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None):
     return res
 
 
-invalid_filename_chars = '<>:"/\\|?*\n\r\t'
+if not shared.cmd_opts.unix_filenames_sanitization:
+    invalid_filename_chars = '#<>:"/\\|?*\n\r\t'
+else:
+    invalid_filename_chars = '/'
 invalid_filename_prefix = ' '
 invalid_filename_postfix = ' .'
 re_nonletters = re.compile(r'[\s' + string.punctuation + ']+')
 re_pattern = re.compile(r"(.*?)(?:\[([^\[\]]+)\]|$)")
 re_pattern_arg = re.compile(r"(.*)<([^>]*)>$")
-max_filename_part_length = 128
+max_filename_part_length = shared.cmd_opts.filenames_max_length
 NOTHING_AND_SKIP_PREVIOUS_TEXT = object()
 
 
@@ -339,8 +352,35 @@ def sanitize_filename_part(text, replace_spaces=True):
     return text
 
 
+@functools.cache
+def get_scheduler_str(sampler_name, scheduler_name):
+    """Returns {Scheduler} if the scheduler is applicable to the sampler"""
+    if scheduler_name == 'Automatic':
+        config = sd_samplers.find_sampler_config(sampler_name)
+        scheduler_name = config.options.get('scheduler', 'Automatic')
+    return scheduler_name.capitalize()
+
+
+@functools.cache
+def get_sampler_scheduler_str(sampler_name, scheduler_name):
+    """Returns the '{Sampler} {Scheduler}' if the scheduler is applicable to the sampler"""
+    return f'{sampler_name} {get_scheduler_str(sampler_name, scheduler_name)}'
+
+
+def get_sampler_scheduler(p, sampler):
+    """Returns '{Sampler} {Scheduler}' / '{Scheduler}' / 'NOTHING_AND_SKIP_PREVIOUS_TEXT'"""
+    if hasattr(p, 'scheduler') and hasattr(p, 'sampler_name'):
+        if sampler:
+            sampler_scheduler = get_sampler_scheduler_str(p.sampler_name, p.scheduler)
+        else:
+            sampler_scheduler = get_scheduler_str(p.sampler_name, p.scheduler)
+        return sanitize_filename_part(sampler_scheduler, replace_spaces=False)
+    return NOTHING_AND_SKIP_PREVIOUS_TEXT
+
+
 class FilenameGenerator:
     replacements = {
+        'basename': lambda self: self.basename or 'img',
         'seed': lambda self: self.seed if self.seed is not None else '',
         'seed_first': lambda self: self.seed if self.p.batch_size == 1 else self.p.all_seeds[0],
         'seed_last': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.batch_size == 1 else self.p.all_seeds[-1],
@@ -350,6 +390,8 @@ class FilenameGenerator:
         'height': lambda self: self.image.height,
         'styles': lambda self: self.p and sanitize_filename_part(", ".join([style for style in self.p.styles if not style == "None"]) or "None", replace_spaces=False),
         'sampler': lambda self: self.p and sanitize_filename_part(self.p.sampler_name, replace_spaces=False),
+        'sampler_scheduler': lambda self: self.p and get_sampler_scheduler(self.p, True),
+        'scheduler': lambda self: self.p and get_sampler_scheduler(self.p, False),
         'model_hash': lambda self: getattr(self.p, "sd_model_hash", shared.sd_model.sd_model_hash),
         'model_name': lambda self: sanitize_filename_part(shared.sd_model.sd_checkpoint_info.name_for_extra, replace_spaces=False),
         'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
@@ -375,12 +417,13 @@ class FilenameGenerator:
     }
     default_time_format = '%Y%m%d%H%M%S'
 
-    def __init__(self, p, seed, prompt, image, zip=False):
+    def __init__(self, p, seed, prompt, image, zip=False, basename=""):
         self.p = p
         self.seed = seed
         self.prompt = prompt
         self.image = image
         self.zip = zip
+        self.basename = basename
 
     def get_vae_filename(self):
         """Get the name of the VAE file."""
@@ -561,6 +604,17 @@ def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_p
             })
 
             piexif.insert(exif_bytes, filename)
+    elif extension.lower() == '.avif':
+        if opts.enable_pnginfo and geninfo is not None:
+            exif_bytes = piexif.dump({
+                "Exif": {
+                    piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(geninfo or "", encoding="unicode")
+                },
+            })
+        else:
+            exif_bytes = None
+
+        image.save(filename,format=image_format, quality=opts.jpeg_quality, exif=exif_bytes)
     elif extension.lower() == ".gif":
         image.save(filename, format=image_format, comment=geninfo)
     else:
@@ -600,12 +654,12 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         txt_fullfn (`str` or None):
             If a text file is saved for this image, this will be its full path. Otherwise None.
     """
-    namegen = FilenameGenerator(p, seed, prompt, image)
+    namegen = FilenameGenerator(p, seed, prompt, image, basename=basename)
 
     # WebP and JPG formats have maximum dimension limits of 16383 and 65535 respectively. switch to PNG which has a much higher limit
     if (image.height > 65535 or image.width > 65535) and extension.lower() in ("jpg", "jpeg") or (image.height > 16383 or image.width > 16383) and extension.lower() == "webp":
         print('Image dimensions too large; saving as PNG')
-        extension = ".png"
+        extension = "png"
 
     if save_to_dirs is None:
         save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt)
@@ -739,10 +793,12 @@ def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]:
             exif_comment = exif_comment.decode('utf8', errors="ignore")
 
         if exif_comment:
-            items['exif comment'] = exif_comment
             geninfo = exif_comment
     elif "comment" in items: # for gif
-        geninfo = items["comment"].decode('utf8', errors="ignore")
+        if isinstance(items["comment"], bytes):
+            geninfo = items["comment"].decode('utf8', errors="ignore")
+        else:
+            geninfo = items["comment"]
 
     for field in IGNORED_INFO_KEYS:
         items.pop(field, None)
@@ -765,7 +821,7 @@ def image_data(data):
     import gradio as gr
 
     try:
-        image = Image.open(io.BytesIO(data))
+        image = read(io.BytesIO(data))
         textinfo, _ = read_info_from_image(image)
         return textinfo, None
     except Exception:
@@ -791,3 +847,31 @@ def flatten(img, bgcolor):
         img = background
 
     return img.convert('RGB')
+
+
+def read(fp, **kwargs):
+    image = Image.open(fp, **kwargs)
+    image = fix_image(image)
+
+    return image
+
+
+def fix_image(image: Image.Image):
+    if image is None:
+        return None
+
+    try:
+        image = ImageOps.exif_transpose(image)
+        image = fix_png_transparency(image)
+    except Exception:
+        pass
+
+    return image
+
+
+def fix_png_transparency(image: Image.Image):
+    if image.mode not in ("RGB", "P") or not isinstance(image.info.get("transparency"), bytes):
+        return image
+
+    image = image.convert("RGBA")
+    return image

modules/img2img.py

@@ -6,8 +6,8 @@ import numpy as np
 from PIL import Image, ImageOps, ImageFilter, ImageEnhance, UnidentifiedImageError
 import gradio as gr
 
-from modules import images as imgutil
-from modules.generation_parameters_copypaste import create_override_settings_dict, parse_generation_parameters
+from modules import images
+from modules.infotext_utils import create_override_settings_dict, parse_generation_parameters
 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, state
 from modules.sd_models import get_closet_checkpoint_match
@@ -17,11 +17,14 @@ from modules.ui import plaintext_to_html
 import modules.scripts
 
 
-def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
+def process_batch(p, input, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
     output_dir = output_dir.strip()
     processing.fix_seed(p)
 
-    images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
+    if isinstance(input, str):
+        batch_images = list(shared.walk_files(input, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
+    else:
+        batch_images = [os.path.abspath(x.name) for x in input]
 
     is_inpaint_batch = False
     if inpaint_mask_dir:
@@ -31,9 +34,9 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
         if is_inpaint_batch:
             print(f"\nInpaint batch is enabled. {len(inpaint_masks)} masks found.")
 
-    print(f"Will process {len(images)} images, creating {p.n_iter * p.batch_size} new images for each.")
+    print(f"Will process {len(batch_images)} images, creating {p.n_iter * p.batch_size} new images for each.")
 
-    state.job_count = len(images) * p.n_iter
+    state.job_count = len(batch_images) * p.n_iter
 
     # extract "default" params to use in case getting png info fails
     prompt = p.prompt
@@ -46,16 +49,16 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
     sd_model_checkpoint_override = get_closet_checkpoint_match(override_settings.get("sd_model_checkpoint", None))
     batch_results = None
     discard_further_results = False
-    for i, image in enumerate(images):
-        state.job = f"{i+1} out of {len(images)}"
+    for i, image in enumerate(batch_images):
+        state.job = f"{i+1} out of {len(batch_images)}"
         if state.skipped:
             state.skipped = False
 
-        if state.interrupted:
+        if state.interrupted or state.stopping_generation:
             break
 
         try:
-            img = Image.open(image)
+            img = images.read(image)
         except UnidentifiedImageError as e:
             print(e)
             continue
@@ -86,7 +89,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
                 # otherwise user has many masks with the same name but different extensions
                 mask_image_path = masks_found[0]
 
-            mask_image = Image.open(mask_image_path)
+            mask_image = images.read(mask_image_path)
             p.image_mask = mask_image
 
         if use_png_info:
@@ -94,8 +97,8 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
                 info_img = img
                 if png_info_dir:
                     info_img_path = os.path.join(png_info_dir, os.path.basename(image))
-                    info_img = Image.open(info_img_path)
-                geninfo, _ = imgutil.read_info_from_image(info_img)
+                    info_img = images.read(info_img_path)
+                geninfo, _ = images.read_info_from_image(info_img)
                 parsed_parameters = parse_generation_parameters(geninfo)
                 parsed_parameters = {k: v for k, v in parsed_parameters.items() if k in (png_info_props or {})}
             except Exception:
@@ -146,7 +149,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
     return batch_results
 
 
-def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_name: str, mask_blur: int, mask_alpha: float, inpainting_fill: int, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
+def img2img(id_task: str, request: gr.Request, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, mask_blur: int, mask_alpha: float, inpainting_fill: int, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, img2img_batch_source_type: str, img2img_batch_upload: list, *args):
     override_settings = create_override_settings_dict(override_settings_texts)
 
     is_batch = mode == 5
@@ -175,9 +178,8 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         image = None
         mask = None
 
-    # Use the EXIF orientation of photos taken by smartphones.
-    if image is not None:
-        image = ImageOps.exif_transpose(image)
+    image = images.fix_image(image)
+    mask = images.fix_image(mask)
 
     if selected_scale_tab == 1 and not is_batch:
         assert image, "Can't scale by because no image is selected"
@@ -194,10 +196,8 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         prompt=prompt,
         negative_prompt=negative_prompt,
         styles=prompt_styles,
-        sampler_name=sampler_name,
         batch_size=batch_size,
         n_iter=n_iter,
-        steps=steps,
         cfg_scale=cfg_scale,
         width=width,
         height=height,
@@ -222,13 +222,17 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     if shared.opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
-    if mask:
-        p.extra_generation_params["Mask blur"] = mask_blur
-
     with closing(p):
         if is_batch:
-            assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
-            processed = process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
+            if img2img_batch_source_type == "upload":
+                assert isinstance(img2img_batch_upload, list) and img2img_batch_upload
+                output_dir = ""
+                inpaint_mask_dir = ""
+                png_info_dir = img2img_batch_png_info_dir if not shared.cmd_opts.hide_ui_dir_config else ""
+                processed = process_batch(p, img2img_batch_upload, output_dir, inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=png_info_dir)
+            else: # "from dir"
+                assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
+                processed = process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
 
             if processed is None:
                 processed = Processed(p, [], p.seed, "")

modules/infotext_utils.py

@@ -4,12 +4,15 @@ import io
 import json
 import os
 import re
+import sys
 
 import gradio as gr
 from modules.paths import data_path
-from modules import shared, ui_tempdir, script_callbacks, processing
+from modules import shared, ui_tempdir, script_callbacks, processing, infotext_versions, images, prompt_parser, errors
 from PIL import Image
 
+sys.modules['modules.generation_parameters_copypaste'] = sys.modules[__name__]  # alias for old name
+
 re_param_code = r'\s*(\w[\w \-/]+):\s*("(?:\\.|[^\\"])+"|[^,]*)(?:,|$)'
 re_param = re.compile(re_param_code)
 re_imagesize = re.compile(r"^(\d+)x(\d+)$")
@@ -28,6 +31,19 @@ class ParamBinding:
         self.paste_field_names = paste_field_names or []
 
 
+class PasteField(tuple):
+    def __new__(cls, component, target, *, api=None):
+        return super().__new__(cls, (component, target))
+
+    def __init__(self, component, target, *, api=None):
+        super().__init__()
+
+        self.api = api
+        self.component = component
+        self.label = target if isinstance(target, str) else None
+        self.function = target if callable(target) else None
+
+
 paste_fields: dict[str, dict] = {}
 registered_param_bindings: list[ParamBinding] = []
 
@@ -67,7 +83,7 @@ def image_from_url_text(filedata):
         assert is_in_right_dir, 'trying to open image file outside of allowed directories'
 
         filename = filename.rsplit('?', 1)[0]
-        return Image.open(filename)
+        return images.read(filename)
 
     if type(filedata) == list:
         if len(filedata) == 0:
@@ -79,11 +95,17 @@ def image_from_url_text(filedata):
         filedata = filedata[len("data:image/png;base64,"):]
 
     filedata = base64.decodebytes(filedata.encode('utf-8'))
-    image = Image.open(io.BytesIO(filedata))
+    image = images.read(io.BytesIO(filedata))
     return image
 
 
 def add_paste_fields(tabname, init_img, fields, override_settings_component=None):
+
+    if fields:
+        for i in range(len(fields)):
+            if not isinstance(fields[i], PasteField):
+                fields[i] = PasteField(*fields[i])
+
     paste_fields[tabname] = {"init_img": init_img, "fields": fields, "override_settings_component": override_settings_component}
 
     # backwards compatibility for existing extensions
@@ -124,18 +146,19 @@ def connect_paste_params_buttons():
         destination_height_component = next(iter([field for field, name in fields if name == "Size-2"] if fields else []), None)
 
         if binding.source_image_component and destination_image_component:
+            need_send_dementions = destination_width_component and binding.tabname != 'inpaint'
             if isinstance(binding.source_image_component, gr.Gallery):
-                func = send_image_and_dimensions if destination_width_component else image_from_url_text
+                func = send_image_and_dimensions if need_send_dementions else image_from_url_text
                 jsfunc = "extract_image_from_gallery"
             else:
-                func = send_image_and_dimensions if destination_width_component else lambda x: x
+                func = send_image_and_dimensions if need_send_dementions else lambda x: x
                 jsfunc = None
 
             binding.paste_button.click(
                 fn=func,
                 _js=jsfunc,
                 inputs=[binding.source_image_component],
-                outputs=[destination_image_component, destination_width_component, destination_height_component] if destination_width_component else [destination_image_component],
+                outputs=[destination_image_component, destination_width_component, destination_height_component] if need_send_dementions else [destination_image_component],
                 show_progress=False,
             )
 
@@ -208,7 +231,7 @@ def restore_old_hires_fix_params(res):
     res['Hires resize-2'] = height
 
 
-def parse_generation_parameters(x: str):
+def parse_generation_parameters(x: str, skip_fields: list[str] | None = None):
     """parses generation parameters string, the one you see in text field under the picture in UI:
 ```
 girl with an artist's beret, determined, blue eyes, desert scene, computer monitors, heavy makeup, by Alphonse Mucha and Charlie Bowater, ((eyeshadow)), (coquettish), detailed, intricate
@@ -218,6 +241,8 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
 
     returns a dict with field values
     """
+    if skip_fields is None:
+        skip_fields = shared.opts.infotext_skip_pasting
 
     res = {}
 
@@ -241,17 +266,6 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         else:
             prompt += ("" if prompt == "" else "\n") + line
 
-    if shared.opts.infotext_styles != "Ignore":
-        found_styles, prompt, negative_prompt = shared.prompt_styles.extract_styles_from_prompt(prompt, negative_prompt)
-
-        if shared.opts.infotext_styles == "Apply":
-            res["Styles array"] = found_styles
-        elif shared.opts.infotext_styles == "Apply if any" and found_styles:
-            res["Styles array"] = found_styles
-
-    res["Prompt"] = prompt
-    res["Negative prompt"] = negative_prompt
-
     for k, v in re_param.findall(lastline):
         try:
             if v[0] == '"' and v[-1] == '"':
@@ -266,6 +280,26 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         except Exception:
             print(f"Error parsing \"{k}: {v}\"")
 
+    # Extract styles from prompt
+    if shared.opts.infotext_styles != "Ignore":
+        found_styles, prompt_no_styles, negative_prompt_no_styles = shared.prompt_styles.extract_styles_from_prompt(prompt, negative_prompt)
+
+        same_hr_styles = True
+        if ("Hires prompt" in res or "Hires negative prompt" in res) and (infotext_ver > infotext_versions.v180_hr_styles if (infotext_ver := infotext_versions.parse_version(res.get("Version"))) else True):
+            hr_prompt, hr_negative_prompt = res.get("Hires prompt", prompt), res.get("Hires negative prompt", negative_prompt)
+            hr_found_styles, hr_prompt_no_styles, hr_negative_prompt_no_styles = shared.prompt_styles.extract_styles_from_prompt(hr_prompt, hr_negative_prompt)
+            if same_hr_styles := found_styles == hr_found_styles:
+                res["Hires prompt"] = '' if hr_prompt_no_styles == prompt_no_styles else hr_prompt_no_styles
+                res['Hires negative prompt'] = '' if hr_negative_prompt_no_styles == negative_prompt_no_styles else hr_negative_prompt_no_styles
+
+        if same_hr_styles:
+            prompt, negative_prompt = prompt_no_styles, negative_prompt_no_styles
+            if (shared.opts.infotext_styles == "Apply if any" and found_styles) or shared.opts.infotext_styles == "Apply":
+                res['Styles array'] = found_styles
+
+    res["Prompt"] = prompt
+    res["Negative prompt"] = negative_prompt
+
     # Missing CLIP skip means it was set to 1 (the default)
     if "Clip skip" not in res:
         res["Clip skip"] = "1"
@@ -281,6 +315,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     if "Hires sampler" not in res:
         res["Hires sampler"] = "Use same sampler"
 
+    if "Hires schedule type" not in res:
+        res["Hires schedule type"] = "Use same scheduler"
+
     if "Hires checkpoint" not in res:
         res["Hires checkpoint"] = "Use same checkpoint"
 
@@ -290,6 +327,18 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     if "Hires negative prompt" not in res:
         res["Hires negative prompt"] = ""
 
+    if "Mask mode" not in res:
+        res["Mask mode"] = "Inpaint masked"
+
+    if "Masked content" not in res:
+        res["Masked content"] = 'original'
+
+    if "Inpaint area" not in res:
+        res["Inpaint area"] = "Whole picture"
+
+    if "Masked area padding" not in res:
+        res["Masked area padding"] = 32
+
     restore_old_hires_fix_params(res)
 
     # Missing RNG means the default was set, which is GPU RNG
@@ -314,8 +363,25 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     if "VAE Decoder" not in res:
         res["VAE Decoder"] = "Full"
 
-    skip = set(shared.opts.infotext_skip_pasting)
-    res = {k: v for k, v in res.items() if k not in skip}
+    if "FP8 weight" not in res:
+        res["FP8 weight"] = "Disable"
+
+    if "Cache FP16 weight for LoRA" not in res and res["FP8 weight"] != "Disable":
+        res["Cache FP16 weight for LoRA"] = False
+
+    prompt_attention = prompt_parser.parse_prompt_attention(prompt)
+    prompt_attention += prompt_parser.parse_prompt_attention(negative_prompt)
+    prompt_uses_emphasis = len(prompt_attention) != len([p for p in prompt_attention if p[1] == 1.0 or p[0] == 'BREAK'])
+    if "Emphasis" not in res and prompt_uses_emphasis:
+        res["Emphasis"] = "Original"
+
+    if "Refiner switch by sampling steps" not in res:
+        res["Refiner switch by sampling steps"] = False
+
+    infotext_versions.backcompat(res)
+
+    for key in skip_fields:
+        res.pop(key, None)
 
     return res
 
@@ -365,13 +431,57 @@ def create_override_settings_dict(text_pairs):
     return res
 
 
+def get_override_settings(params, *, skip_fields=None):
+    """Returns a list of settings overrides from the infotext parameters dictionary.
+
+    This function checks the `params` dictionary for any keys that correspond to settings in `shared.opts` and returns
+    a list of tuples containing the parameter name, setting name, and new value cast to correct type.
+
+    It checks for conditions before adding an override:
+    - ignores settings that match the current value
+    - ignores parameter keys present in skip_fields argument.
+
+    Example input:
+        {"Clip skip": "2"}
+
+    Example output:
+        [("Clip skip", "CLIP_stop_at_last_layers", 2)]
+    """
+
+    res = []
+
+    mapping = [(info.infotext, k) for k, info in shared.opts.data_labels.items() if info.infotext]
+    for param_name, setting_name in mapping + infotext_to_setting_name_mapping:
+        if param_name in (skip_fields or {}):
+            continue
+
+        v = params.get(param_name, None)
+        if v is None:
+            continue
+
+        if setting_name == "sd_model_checkpoint" and shared.opts.disable_weights_auto_swap:
+            continue
+
+        v = shared.opts.cast_value(setting_name, v)
+        current_value = getattr(shared.opts, setting_name, None)
+
+        if v == current_value:
+            continue
+
+        res.append((param_name, setting_name, v))
+
+    return res
+
+
 def connect_paste(button, paste_fields, input_comp, override_settings_component, tabname):
     def paste_func(prompt):
-        if not prompt and not shared.cmd_opts.hide_ui_dir_config:
+        if not prompt and not shared.cmd_opts.hide_ui_dir_config and not shared.cmd_opts.no_prompt_history:
             filename = os.path.join(data_path, "params.txt")
-            if os.path.exists(filename):
+            try:
                 with open(filename, "r", encoding="utf8") as file:
                     prompt = file.read()
+            except OSError:
+                pass
 
         params = parse_generation_parameters(prompt)
         script_callbacks.infotext_pasted_callback(prompt, params)
@@ -379,7 +489,11 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
 
         for output, key in paste_fields:
             if callable(key):
-                v = key(params)
+                try:
+                    v = key(params)
+                except Exception:
+                    errors.report(f"Error executing {key}", exc_info=True)
+                    v = None
             else:
                 v = params.get(key, None)
 
@@ -393,6 +507,8 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
 
                     if valtype == bool and v == "False":
                         val = False
+                    elif valtype == int:
+                        val = float(v)
                     else:
                         val = valtype(v)
 
@@ -406,29 +522,9 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
         already_handled_fields = {key: 1 for _, key in paste_fields}
 
         def paste_settings(params):
-            vals = {}
+            vals = get_override_settings(params, skip_fields=already_handled_fields)
 
-            mapping = [(info.infotext, k) for k, info in shared.opts.data_labels.items() if info.infotext]
-            for param_name, setting_name in mapping + infotext_to_setting_name_mapping:
-                if param_name in already_handled_fields:
-                    continue
-
-                v = params.get(param_name, None)
-                if v is None:
-                    continue
-
-                if setting_name == "sd_model_checkpoint" and shared.opts.disable_weights_auto_swap:
-                    continue
-
-                v = shared.opts.cast_value(setting_name, v)
-                current_value = getattr(shared.opts, setting_name, None)
-
-                if v == current_value:
-                    continue
-
-                vals[param_name] = v
-
-            vals_pairs = [f"{k}: {v}" for k, v in vals.items()]
+            vals_pairs = [f"{infotext_text}: {value}" for infotext_text, setting_name, value in vals]
 
             return gr.Dropdown.update(value=vals_pairs, choices=vals_pairs, visible=bool(vals_pairs))
 

modules/infotext_versions.py

@@ -0,0 +1,46 @@
+from modules import shared
+from packaging import version
+import re
+
+
+v160 = version.parse("1.6.0")
+v170_tsnr = version.parse("v1.7.0-225")
+v180 = version.parse("1.8.0")
+v180_hr_styles = version.parse("1.8.0-139")
+
+
+def parse_version(text):
+    if text is None:
+        return None
+
+    m = re.match(r'([^-]+-[^-]+)-.*', text)
+    if m:
+        text = m.group(1)
+
+    try:
+        return version.parse(text)
+    except Exception:
+        return None
+
+
+def backcompat(d):
+    """Checks infotext Version field, and enables backwards compatibility options according to it."""
+
+    if not shared.opts.auto_backcompat:
+        return
+
+    ver = parse_version(d.get("Version"))
+    if ver is None:
+        return
+
+    if ver < v160 and '[' in d.get('Prompt', ''):
+        d["Old prompt editing timelines"] = True
+
+    if ver < v160 and d.get('Sampler', '') in ('DDIM', 'PLMS'):
+        d["Pad conds v0"] = True
+
+    if ver < v170_tsnr:
+        d["Downcast alphas_cumprod"] = True
+
+    if ver < v180 and d.get('Refiner'):
+        d["Refiner switch by sampling steps"] = True

modules/initialize.py

@@ -1,5 +1,6 @@
 import importlib
 import logging
+import os
 import sys
 import warnings
 from threading import Thread
@@ -18,6 +19,7 @@ def imports():
     warnings.filterwarnings(action="ignore", category=DeprecationWarning, module="pytorch_lightning")
     warnings.filterwarnings(action="ignore", category=UserWarning, module="torchvision")
 
+    os.environ.setdefault('GRADIO_ANALYTICS_ENABLED', 'False')
     import gradio  # noqa: F401
     startup_timer.record("import gradio")
 
@@ -49,14 +51,12 @@ def check_versions():
 def initialize():
     from modules import initialize_util
     initialize_util.fix_torch_version()
+    initialize_util.fix_pytorch_lightning()
     initialize_util.fix_asyncio_event_loop_policy()
     initialize_util.validate_tls_options()
     initialize_util.configure_sigint_handler()
     initialize_util.configure_opts_onchange()
 
-    from modules import modelloader
-    modelloader.cleanup_models()
-
     from modules import sd_models
     sd_models.setup_model()
     startup_timer.record("setup SD model")
@@ -110,7 +110,7 @@ def initialize_rest(*, reload_script_modules=False):
     with startup_timer.subcategory("load scripts"):
         scripts.load_scripts()
 
-    if reload_script_modules:
+    if reload_script_modules and shared.opts.enable_reloading_ui_scripts:
         for module in [module for name, module in sys.modules.items() if name.startswith("modules.ui")]:
             importlib.reload(module)
         startup_timer.record("reload script modules")
@@ -140,16 +140,17 @@ def initialize_rest(*, reload_script_modules=False):
         """
         Accesses shared.sd_model property to load model.
         After it's available, if it has been loaded before this access by some extension,
-        its optimization may be None because the list of optimizaers has neet been filled
+        its optimization may be None because the list of optimizers has not been filled
         by that time, so we apply optimization again.
         """
+        from modules import devices
+        devices.torch_npu_set_device()
 
         shared.sd_model  # noqa: B018
 
         if sd_hijack.current_optimizer is None:
             sd_hijack.apply_optimizations()
 
-        from modules import devices
         devices.first_time_calculation()
     if not shared.cmd_opts.skip_load_model_at_start:
         Thread(target=load_model).start()

modules/initialize_util.py

@@ -24,6 +24,13 @@ def fix_torch_version():
         torch.__long_version__ = torch.__version__
         torch.__version__ = re.search(r'[\d.]+[\d]', torch.__version__).group(0)
 
+def fix_pytorch_lightning():
+    # Checks if pytorch_lightning.utilities.distributed already exists in the sys.modules cache
+    if 'pytorch_lightning.utilities.distributed' not in sys.modules:
+        import pytorch_lightning
+        # Lets the user know that the library was not found and then will set it to pytorch_lightning.utilities.rank_zero
+        print("Pytorch_lightning.distributed not found, attempting pytorch_lightning.rank_zero")
+        sys.modules["pytorch_lightning.utilities.distributed"] = pytorch_lightning.utilities.rank_zero
 
 def fix_asyncio_event_loop_policy():
     """
@@ -177,6 +184,8 @@ def configure_opts_onchange():
     shared.opts.onchange("temp_dir", ui_tempdir.on_tmpdir_changed)
     shared.opts.onchange("gradio_theme", shared.reload_gradio_theme)
     shared.opts.onchange("cross_attention_optimization", wrap_queued_call(lambda: sd_hijack.model_hijack.redo_hijack(shared.sd_model)), call=False)
+    shared.opts.onchange("fp8_storage", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
+    shared.opts.onchange("cache_fp16_weight", wrap_queued_call(lambda: sd_models.reload_model_weights(forced_reload=True)), call=False)
     startup_timer.record("opts onchange")
 
 

modules/interrogate.py

@@ -10,14 +10,14 @@ import torch.hub
 from torchvision import transforms
 from torchvision.transforms.functional import InterpolationMode
 
-from modules import devices, paths, shared, lowvram, modelloader, errors
+from modules import devices, paths, shared, lowvram, modelloader, errors, torch_utils
 
 blip_image_eval_size = 384
 clip_model_name = 'ViT-L/14'
 
 Category = namedtuple("Category", ["name", "topn", "items"])
 
-re_topn = re.compile(r"\.top(\d+)\.")
+re_topn = re.compile(r"\.top(\d+)$")
 
 def category_types():
     return [f.stem for f in Path(shared.interrogator.content_dir).glob('*.txt')]
@@ -131,7 +131,7 @@ class InterrogateModels:
 
         self.clip_model = self.clip_model.to(devices.device_interrogate)
 
-        self.dtype = next(self.clip_model.parameters()).dtype
+        self.dtype = torch_utils.get_param(self.clip_model).dtype
 
     def send_clip_to_ram(self):
         if not shared.opts.interrogate_keep_models_in_memory:

modules/launch_utils.py

@@ -9,6 +9,7 @@ import importlib.util
 import importlib.metadata
 import platform
 import json
+import shlex
 from functools import lru_cache
 
 from modules import cmd_args, errors
@@ -27,8 +28,7 @@ dir_repos = "repositories"
 # Whether to default to printing command output
 default_command_live = (os.environ.get('WEBUI_LAUNCH_LIVE_OUTPUT') == "1")
 
-if 'GRADIO_ANALYTICS_ENABLED' not in os.environ:
-    os.environ['GRADIO_ANALYTICS_ENABLED'] = 'False'
+os.environ.setdefault('GRADIO_ANALYTICS_ENABLED', 'False')
 
 
 def check_python_version():
@@ -56,7 +56,7 @@ and delete current Python and "venv" folder in WebUI's directory.
 
 You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
 
-{"Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases" if is_windows else ""}
+{"Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre" if is_windows else ""}
 
 Use --skip-python-version-check to suppress this warning.
 """)
@@ -77,7 +77,7 @@ def git_tag():
     except Exception:
         try:
 
-            changelog_md = os.path.join(os.path.dirname(os.path.dirname(__file__)), "CHANGELOG.md")
+            changelog_md = os.path.join(script_path, "CHANGELOG.md")
             with open(changelog_md, "r", encoding="utf-8") as file:
                 line = next((line.strip() for line in file if line.strip()), "<none>")
                 line = line.replace("## ", "")
@@ -189,7 +189,7 @@ def git_clone(url, dir, name, commithash=None):
         return
 
     try:
-        run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
+        run(f'"{git}" clone --config core.filemode=false "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
     except RuntimeError:
         shutil.rmtree(dir, ignore_errors=True)
         raise
@@ -232,7 +232,7 @@ def run_extension_installer(extension_dir):
 
     try:
         env = os.environ.copy()
-        env['PYTHONPATH'] = f"{os.path.abspath('.')}{os.pathsep}{env.get('PYTHONPATH', '')}"
+        env['PYTHONPATH'] = f"{script_path}{os.pathsep}{env.get('PYTHONPATH', '')}"
 
         stdout = run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env).strip()
         if stdout:
@@ -245,11 +245,13 @@ def list_extensions(settings_file):
     settings = {}
 
     try:
-        if os.path.isfile(settings_file):
-            with open(settings_file, "r", encoding="utf8") as file:
-                settings = json.load(file)
+        with open(settings_file, "r", encoding="utf8") as file:
+            settings = json.load(file)
+    except FileNotFoundError:
+        pass
     except Exception:
-        errors.report("Could not load settings", exc_info=True)
+        errors.report(f'\nCould not load settings\nThe config file "{settings_file}" is likely corrupted\nIt has been moved to the "tmp/config.json"\nReverting config to default\n\n''', exc_info=True)
+        os.replace(settings_file, os.path.join(script_path, "tmp", "config.json"))
 
     disabled_extensions = set(settings.get('disabled_extensions', []))
     disable_all_extensions = settings.get('disable_all_extensions', 'none')
@@ -314,8 +316,8 @@ def requirements_met(requirements_file):
 
 
 def prepare_environment():
-    torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu118")
-    torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url {torch_index_url}")
+    torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu121")
+    torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.1.2 torchvision==0.16.2 --extra-index-url {torch_index_url}")
     if args.use_ipex:
         if platform.system() == "Windows":
             # The "Nuullll/intel-extension-for-pytorch" wheels were built from IPEX source for Intel Arc GPU: https://github.com/intel/intel-extension-for-pytorch/tree/xpu-main
@@ -337,21 +339,22 @@ def prepare_environment():
             torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://pytorch-extension.intel.com/release-whl/stable/xpu/us/")
             torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.0a0 intel-extension-for-pytorch==2.0.110+gitba7f6c1 --extra-index-url {torch_index_url}")
     requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
+    requirements_file_for_npu = os.environ.get('REQS_FILE_FOR_NPU', "requirements_npu.txt")
 
-    xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.20')
+    xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.23.post1')
     clip_package = os.environ.get('CLIP_PACKAGE', "https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip")
     openclip_package = os.environ.get('OPENCLIP_PACKAGE', "https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip")
 
+    assets_repo = os.environ.get('ASSETS_REPO', "https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets.git")
     stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git")
     stable_diffusion_xl_repo = os.environ.get('STABLE_DIFFUSION_XL_REPO', "https://github.com/Stability-AI/generative-models.git")
     k_diffusion_repo = os.environ.get('K_DIFFUSION_REPO', 'https://github.com/crowsonkb/k-diffusion.git')
-    codeformer_repo = os.environ.get('CODEFORMER_REPO', 'https://github.com/sczhou/CodeFormer.git')
     blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
 
+    assets_commit_hash = os.environ.get('ASSETS_COMMIT_HASH', "6f7db241d2f8ba7457bac5ca9753331f0c266917")
     stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
     stable_diffusion_xl_commit_hash = os.environ.get('STABLE_DIFFUSION_XL_COMMIT_HASH', "45c443b316737a4ab6e40413d7794a7f5657c19f")
     k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "ab527a9a6d347f364e3d185ba6d714e22d80cb3c")
-    codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
     blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
 
     try:
@@ -405,18 +408,14 @@ def prepare_environment():
 
     os.makedirs(os.path.join(script_path, dir_repos), exist_ok=True)
 
+    git_clone(assets_repo, repo_dir('stable-diffusion-webui-assets'), "assets", assets_commit_hash)
     git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
     git_clone(stable_diffusion_xl_repo, repo_dir('generative-models'), "Stable Diffusion XL", stable_diffusion_xl_commit_hash)
     git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
-    git_clone(codeformer_repo, repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
     git_clone(blip_repo, repo_dir('BLIP'), "BLIP", blip_commit_hash)
 
     startup_timer.record("clone repositores")
 
-    if not is_installed("lpips"):
-        run_pip(f"install -r \"{os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}\"", "requirements for CodeFormer")
-        startup_timer.record("install CodeFormer requirements")
-
     if not os.path.isfile(requirements_file):
         requirements_file = os.path.join(script_path, requirements_file)
 
@@ -424,6 +423,13 @@ def prepare_environment():
         run_pip(f"install -r \"{requirements_file}\"", "requirements")
         startup_timer.record("install requirements")
 
+    if not os.path.isfile(requirements_file_for_npu):
+        requirements_file_for_npu = os.path.join(script_path, requirements_file_for_npu)
+
+    if "torch_npu" in torch_command and not requirements_met(requirements_file_for_npu):
+        run_pip(f"install -r \"{requirements_file_for_npu}\"", "requirements_for_npu")
+        startup_timer.record("install requirements_for_npu")
+
     if not args.skip_install:
         run_extensions_installers(settings_file=args.ui_settings_file)
 
@@ -440,7 +446,6 @@ def prepare_environment():
         exit(0)
 
 
-
 def configure_for_tests():
     if "--api" not in sys.argv:
         sys.argv.append("--api")
@@ -456,7 +461,7 @@ def configure_for_tests():
 
 
 def start():
-    print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with arguments: {' '.join(sys.argv[1:])}")
+    print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with arguments: {shlex.join(sys.argv[1:])}")
     import webui
     if '--nowebui' in sys.argv:
         webui.api_only()

modules/logging_config.py

@@ -1,41 +1,58 @@
-import os
 import logging
+import os
 
 try:
-    from tqdm.auto import tqdm
+    from tqdm import tqdm
+
 
     class TqdmLoggingHandler(logging.Handler):
-        def __init__(self, level=logging.INFO):
-            super().__init__(level)
+        def __init__(self, fallback_handler: logging.Handler):
+            super().__init__()
+            self.fallback_handler = fallback_handler
 
         def emit(self, record):
             try:
-                msg = self.format(record)
-                tqdm.write(msg)
-                self.flush()
+                # If there are active tqdm progress bars,
+                # attempt to not interfere with them.
+                if tqdm._instances:
+                    tqdm.write(self.format(record))
+                else:
+                    self.fallback_handler.emit(record)
             except Exception:
-                self.handleError(record)
+                self.fallback_handler.emit(record)
 
-    TQDM_IMPORTED = True
 except ImportError:
-    # tqdm does not exist before first launch
-    # I will import once the UI finishes seting up the enviroment and reloads.
-    TQDM_IMPORTED = False
+    TqdmLoggingHandler = None
+
 
 def setup_logging(loglevel):
     if loglevel is None:
         loglevel = os.environ.get("SD_WEBUI_LOG_LEVEL")
 
-    loghandlers = []
+    if not loglevel:
+        return
 
-    if TQDM_IMPORTED:
-        loghandlers.append(TqdmLoggingHandler())
+    if logging.root.handlers:
+        # Already configured, do not interfere
+        return
 
-    if loglevel:
-        log_level = getattr(logging, loglevel.upper(), None) or logging.INFO
-        logging.basicConfig(
-            level=log_level,
-            format='%(asctime)s %(levelname)s [%(name)s] %(message)s',
-            datefmt='%Y-%m-%d %H:%M:%S',
-            handlers=loghandlers
-        )
+    formatter = logging.Formatter(
+        '%(asctime)s %(levelname)s [%(name)s] %(message)s',
+        '%Y-%m-%d %H:%M:%S',
+    )
+
+    if os.environ.get("SD_WEBUI_RICH_LOG"):
+        from rich.logging import RichHandler
+        handler = RichHandler()
+    else:
+        handler = logging.StreamHandler()
+        handler.setFormatter(formatter)
+
+    if TqdmLoggingHandler:
+        handler = TqdmLoggingHandler(handler)
+
+    handler.setFormatter(formatter)
+
+    log_level = getattr(logging, loglevel.upper(), None) or logging.INFO
+    logging.root.setLevel(log_level)
+    logging.root.addHandler(handler)