diff --git a/README.md b/README.md index 41730012c..52a4f1bf5 100644 --- a/README.md +++ b/README.md @@ -4,8 +4,9 @@ A browser interface based on Gradio library for Stable Diffusion. Original script with Gradio UI was written by a kind anonymopus user. This is a modification. ![](screenshot.png) +## Installing and running -## Stable Diffusion +### Stable Diffusion This script assumes that you already have main Stable Diffusion sutff installed, assumed to be in directory `/sd`. If you don't have it installed, follow the guide: @@ -21,7 +22,7 @@ Particularly, following files must exist: - `/sd/ldm/util.py` - `/sd/k_diffusion/__init__.py` -## GFPGAN +### GFPGAN If you want to use GFPGAN to improve generated faces, you need to install it separately. Follow instructions from https://github.com/TencentARC/GFPGAN, but when cloning it, do so into Stable Diffusion main directory, `/sd`. @@ -37,7 +38,7 @@ The following files must exist: If the GFPGAN directory does not exist, you will not get the option to use GFPGAN in the UI. If it does exist, you will either be able to use it, or there will be a message in console with an error related to GFPGAN. -## Web UI +### Web UI Run the script as: @@ -56,3 +57,44 @@ Running on local URL: http://127.0.0.1:7860/ ``` Open the URL in browser, and you are good to go. + +## Features +The script creates a web UI for Stable Diffusion's txt2img and img2img scripts. Following are features added +that are not in original script. + +### GFPGAN +Lets you improve faces in pictures using the GFPGAN model. There is a checkbox in every tab to use GFPGAN at 100%, and +also a separate tab that just allows you to use GFPGAN on any picture, with a slider that controls how strongthe effect is. + +![](images/GFPGAN.png) + +### Sampling method selection +Pick out of three sampling methods for txt2img: DDIM, PLMS, k-diffusion: + +![](images/sampling.png) + +### Prompt matrix +Separate multiple prompts using the `|` character, and the system will produce an image for every combination of them. +For example, if you use `a house in a field of grass|at dawn|illustration` prompt, there are four combinations possible (first part of prompt is always kept): + +- `a house in a field of grass` +- `a house in a field of grass, at dawn` +- `a house in a field of grass, illustration` +- `a house in a field of grass, at dawn, illustration` + +Four images will be produced, in this order, all with same seed and each with corresponding prompt: + +![](images/prompt-matrix.png) + +### Flagging +Click the Flag button under the output section, and generated images will be saved to `log/images` directory, and generation parameters +will be appended to a csv file `log/log.csv` in the `/sd` directory. + +### Copy-paste generation parameters +A text output provides generation parameters in an easy to copy-paste form for easy sharing. + +![](images/kopipe.png) + +### Correct seeds for batches +If you use a seed of 1000 to generate two batches of two images each, four generated images will have seeds: `1000, 1001, 1002, 1003`. +Previous versions of the UI would produce `1000, x, 1001, x`, where x is an iamge that can't be generated by any seed. diff --git a/images/GFPGAN.png b/images/GFPGAN.png new file mode 100644 index 000000000..bd42c0118 Binary files /dev/null and b/images/GFPGAN.png differ diff --git a/images/kopipe.png b/images/kopipe.png new file mode 100644 index 000000000..105ddd6aa Binary files /dev/null and b/images/kopipe.png differ diff --git a/images/prompt-matrix.png b/images/prompt-matrix.png new file mode 100644 index 000000000..53ba92b6e Binary files /dev/null and b/images/prompt-matrix.png differ diff --git a/images/sampling.png b/images/sampling.png new file mode 100644 index 000000000..7d62177de Binary files /dev/null and b/images/sampling.png differ diff --git a/webui.py b/webui.py index 5b990a5f9..1a2fa56c9 100644 --- a/webui.py +++ b/webui.py @@ -13,13 +13,20 @@ from contextlib import contextmanager, nullcontext import mimetypes import random import math -import csv import k_diffusion as K from ldm.util import instantiate_from_config from ldm.models.diffusion.ddim import DDIMSampler from ldm.models.diffusion.plms import PLMSSampler +try: + # this silences the annoying "Some weights of the model checkpoint were not used when initializing..." message at start. + + from transformers import logging + logging.set_verbosity_error() +except: + pass + # this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the bowser will not show any UI mimetypes.init() mimetypes.add_type('application/javascript', '.js') @@ -28,7 +35,7 @@ mimetypes.add_type('application/javascript', '.js') opt_C = 4 opt_f = 8 -invalid_filename_chars = '<>:"/\|?*' +invalid_filename_chars = '<>:"/\|?*\n' parser = argparse.ArgumentParser() parser.add_argument("--outdir", type=str, nargs="?", help="dir to write results to", default=None) @@ -121,7 +128,6 @@ if os.path.exists(GFPGAN_dir): print("Error loading GFPGAN:", file=sys.stderr) print(traceback.format_exc(), file=sys.stderr) - config = OmegaConf.load("configs/stable-diffusion/v1-inference.yaml") model = load_model_from_config(config, "models/ldm/stable-diffusion-v1/model.ckpt") @@ -296,7 +302,9 @@ class Flagging(gr.FlaggingCallback): def setup(self, components, flagging_dir: str): pass - def flag(self, flag_data, flag_option=None, flag_index=None, username=None) -> int: + def flag(self, flag_data, flag_option=None, flag_index=None, username=None): + import csv + os.makedirs("log/images", exist_ok=True) # those must match the "dream" function @@ -341,7 +349,7 @@ dream_interface = gr.Interface( gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="DDIM ETA", value=0.0, visible=False), gr.Slider(minimum=1, maximum=16, step=1, label='Batch count (how many batches of images to generate)', value=1), gr.Slider(minimum=1, maximum=4, step=1, label='Batch size (how many images are in a batch; memory-hungry)', value=1), - gr.Slider(minimum=1.0, maximum=15.0, step=0.5, label='Classifier Free Guidance Scale (how strongly should the image follow the prompt)', value=7.0), + gr.Slider(minimum=1.0, maximum=15.0, step=0.5, label='Classifier Free Guidance Scale (how strongly the image should follow the prompt)', value=7.0), gr.Number(label='Seed', value=-1), gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512), gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512), @@ -456,13 +464,13 @@ img2img_interface = gr.Interface( gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=50), gr.Checkbox(label='Fix faces using GFPGAN', value=False, visible=GFPGAN is not None), gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="DDIM ETA", value=0.0, visible=False), - gr.Slider(minimum=1, maximum=16, step=1, label='Sampling iterations', value=1), - gr.Slider(minimum=1, maximum=4, step=1, label='Samples per iteration', value=1), - gr.Slider(minimum=1.0, maximum=15.0, step=0.5, label='Classifier Free Guidance Scale', value=7.0), + gr.Slider(minimum=1, maximum=16, step=1, label='Batch count (how many batches of images to generate)', value=1), + gr.Slider(minimum=1, maximum=4, step=1, label='Batch size (how many images are in a batch; memory-hungry)', value=1), + gr.Slider(minimum=1.0, maximum=15.0, step=0.5, label='Classifier Free Guidance Scale (how strongly the image should follow the prompt)', value=7.0), gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising Strength', value=0.75), gr.Number(label='Seed', value=-1), - gr.Slider(minimum=64, maximum=2048, step=64, label="Resize Height", value=512), - gr.Slider(minimum=64, maximum=2048, step=64, label="Resize Width", value=512), + gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512), + gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512), ], outputs=[ gr.Gallery(), @@ -470,11 +478,12 @@ img2img_interface = gr.Interface( ], title="Stable Diffusion Image-to-Image", description="Generate images from images with Stable Diffusion", + allow_flagging="never", ) interfaces = [ - (dream_interface, "Dream"), - (img2img_interface, "Image Translation") + (dream_interface, "txt2img"), + (img2img_interface, "img2img") ] def run_GFPGAN(image, strength): @@ -501,6 +510,7 @@ if GFPGAN is not None: ], title="GFPGAN", description="Fix faces on images", + allow_flagging="never", ), "GFPGAN")) demo = gr.TabbedInterface(interface_list=[x[0] for x in interfaces], tab_names=[x[1] for x in interfaces])