brkirch 35b1775b32 Use other MPS optimization for large q.shape[0] * q.shape[1] ...

Check if q.shape[0] * q.shape[1] is 2**18 or larger and use the lower memory usage MPS optimization if it is. This should prevent most crashes that were occurring at certain resolutions (e.g. 1024x1024, 2048x512, 512x2048).

Also included is a change to check slice_size and prevent it from being divisible by 4096 which also results in a crash. Otherwise a crash can occur at 1024x512 or 512x1024 resolution.

2022-12-20 21:30:00 -05:00

..

api

Bug fix

2022-12-09 23:03:06 +09:00

codeformer

clarification for settings; another comment about copied files

2022-09-07 12:57:12 +03:00

hypernetworks

Merge branch 'master' into racecond_fix

2022-12-03 10:19:51 +03:00

textual_inversion

Merge branch 'master' into racecond_fix

2022-12-03 10:19:51 +03:00

artists.py

added random artist button

2022-09-05 23:08:06 +03:00

call_queue.py

fix an error that happens when you type into prompt while switching model, put queue stuff into separate file

2022-11-28 09:00:10 +03:00

codeformer_model.py

Set device for facelib/facexlib and gfpgan

2022-11-12 03:34:13 -05:00

deepbooru_model.py

moved deepdanbooru to pure pytorch implementation

2022-11-20 16:39:20 +03:00

deepbooru.py

fix incorrect file extension filter for deepdanbooru models

2022-12-03 18:46:09 +03:00

devices.py

add built-in extension system

2022-12-03 18:06:33 +03:00

errors.py

Allow TF32 in CUDA for increased performance #279

2022-09-12 16:34:13 +03:00

esrgan_model_arch.py

fix typo in filename for ESRGAN arch

2022-10-09 15:08:27 +03:00

esrgan_model.py

Revert "MPS Upscalers Fix"

2022-11-17 00:08:21 -05:00

extensions.py

add built-in extension system

2022-12-03 18:06:33 +03:00

extras.py

extras.py: use as little RAM as possible, misc fixes

2022-12-04 10:31:06 -05:00

face_restoration.py

codeformer support

2022-09-07 12:32:28 +03:00

generation_parameters_copypaste.py

Merge pull request #5441 from timntorres/add-5433-avoid-sending-size-option

2022-12-10 11:07:16 +03:00

gfpgan_model.py

Set device for facelib/facexlib and gfpgan

2022-11-12 03:34:13 -05:00

images.py

Merge pull request #5119 from 0xb8/master

2022-12-10 13:26:07 +03:00

img2img.py

fix #4459 breaking inpainting when the option is not specified.

2022-12-04 01:04:24 +03:00

interrogate.py

use modelloader for #4956

2022-12-03 18:45:51 +03:00

localization.py

add ability to create extensions that add localizations

2022-11-06 09:02:35 +03:00

lowvram.py

make SD2 compatible with --medvram setting

2022-11-26 20:52:16 +03:00

masking.py

Fix non-square full resolution inpainting.

2022-10-30 15:33:02 -07:00

memmon.py

Add some error handling for VRAM monitor

2022-09-18 05:20:33 -04:00

modelloader.py

add built-in extension system

2022-12-03 18:06:33 +03:00

ngrok.py

Merge branch 'master' into patch-1

2022-11-11 21:14:10 +07:00

paths.py

Add support Stable Diffusion 2.0

2022-11-26 16:10:46 +03:00

processing.py

Merge pull request #5191 from aliencaocao/enable_checkpoint_switching_in_override_settings

2022-12-10 16:29:40 +03:00

prompt_parser.py

Fix typo in prompt_parser.py

2022-10-19 11:52:12 +03:00

realesrgan_model.py

Removed duplicate definition model_path

2022-10-09 12:46:07 +03:00

safe.py

Fixed safe.py for pytorch 1.13 ckpt files

2022-12-02 11:12:13 +01:00

script_callbacks.py

Add API for scripts to add elements anywhere in UI.

2022-11-19 19:10:28 +03:00

script_loading.py

make existing script loading and new preload code use same code for loading modules

2022-11-12 10:56:06 +03:00

scripts.py

remove NSFW filter and its dependency; if you still want it, find it in the extensions section

2022-12-10 14:54:16 +03:00

sd_hijack_checkpoint.py

Gradient accumulation, autocast fix, new latent sampling method, etc

2022-11-20 12:35:26 +09:00

sd_hijack_clip.py

Add support Stable Diffusion 2.0

2022-11-26 16:10:46 +03:00

sd_hijack_inpainting.py

Add support Stable Diffusion 2.0

2022-11-26 16:10:46 +03:00

sd_hijack_open_clip.py

Add support Stable Diffusion 2.0

2022-11-26 16:10:46 +03:00

sd_hijack_optimizations.py

Use other MPS optimization for large q.shape[0] * q.shape[1]

2022-12-20 21:30:00 -05:00

sd_hijack_unet.py

do not replace entire unet for the resolution hack

2022-12-10 09:14:45 +03:00

sd_hijack.py

cleanup some unneeded imports for hijack files

2022-12-10 09:17:39 +03:00

sd_models.py

Merge pull request #4841 from R-N/vae-fix-none

2022-12-10 09:58:20 +03:00

sd_samplers.py

Rework MPS randn fix, add randn_like fix

2022-11-30 10:33:42 -05:00

sd_vae.py

Merge branch 'a1111' into vae-fix-none

2022-11-19 16:38:21 +07:00

shared.py

remove NSFW filter and its dependency; if you still want it, find it in the extensions section

2022-12-10 14:54:16 +03:00

styles.py

make it possible for StableDiffusionProcessing to accept multiple different negative prompts in a batch

2022-11-19 13:23:25 +03:00

txt2img.py

change StableDiffusionProcessing to internally use sampler name instead of sampler index

2022-11-19 12:01:51 +03:00

ui_extensions.py

add an 'installed' tag to extensions

2022-12-10 15:05:22 +03:00

ui_tempdir.py

if image on disk was deleted between being generated and request being completed, do use temporary dir to store it for the browser

2022-11-27 23:14:13 +03:00

ui.py

use less javascript for this non-js-only implementation of the clear prompt button.

2022-12-10 13:46:18 +03:00

upscaler.py

fix upscale loop erroneously applied multiple times

2022-11-04 22:56:18 +03:00