From 4269e8c15563f26be9011501e308a078fd5ecbb2 Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Sun, 22 Jan 2023 10:21:12 -0500 Subject: [PATCH] complete merge --- README.md | 189 ++++-------------- config.json | 4 +- .../sd-extension-steps-animation | 2 +- modules/shared.py | 2 +- wiki | 2 +- 5 files changed, 47 insertions(+), 152 deletions(-) diff --git a/README.md b/README.md index 9c0cd1ef7..71063d887 100644 --- a/README.md +++ b/README.md @@ -1,160 +1,55 @@ -# Stable Diffusion web UI -A browser interface based on Gradio library for Stable Diffusion. +# Stable Diffusion - Automatic -![](screenshot.png) +*Heavily opinionated custom fork of* -## Features -[Detailed feature showcase with images](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features): -- Original txt2img and img2img modes -- One click install and run script (but you still must install python and git) -- Outpainting -- Inpainting -- Color Sketch -- Prompt Matrix -- Stable Diffusion Upscale -- Attention, specify parts of text that the model should pay more attention to - - a man in a ((tuxedo)) - will pay more attention to tuxedo - - a man in a (tuxedo:1.21) - alternative syntax - - select text and press ctrl+up or ctrl+down to automatically adjust attention to selected text (code contributed by anonymous user) -- Loopback, run img2img processing multiple times -- X/Y plot, a way to draw a 2 dimensional plot of images with different parameters -- Textual Inversion - - have as many embeddings as you want and use any names you like for them - - use multiple embeddings with different numbers of vectors per token - - works with half precision floating point numbers - - train embeddings on 8GB (also reports of 6GB working) -- Extras tab with: - - GFPGAN, neural network that fixes faces - - CodeFormer, face restoration tool as an alternative to GFPGAN - - RealESRGAN, neural network upscaler - - ESRGAN, neural network upscaler with a lot of third party models - - SwinIR and Swin2SR([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers - - LDSR, Latent diffusion super resolution upscaling -- Resizing aspect ratio options -- Sampling method selection - - Adjust sampler eta values (noise multiplier) - - More advanced noise setting options -- Interrupt processing at any time -- 4GB video card support (also reports of 2GB working) -- Correct seeds for batches -- Live prompt token length validation -- Generation parameters - - parameters you used to generate images are saved with that image - - in PNG chunks for PNG, in EXIF for JPEG - - can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI - - can be disabled in settings - - drag and drop an image/text-parameters to promptbox -- Read Generation Parameters Button, loads parameters in promptbox to UI -- Settings page -- Running arbitrary python code from UI (must run with --allow-code to enable) -- Mouseover hints for most UI elements -- Possible to change defaults/mix/max/step values for UI elements via text config -- Tiling support, a checkbox to create images that can be tiled like textures -- Progress bar and live image generation preview - - Can use a separate neural network to produce previews with almost none VRAM or compute requirement -- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image -- Styles, a way to save part of prompt and easily apply them via dropdown later -- Variations, a way to generate same image but with tiny differences -- Seed resizing, a way to generate same image but at slightly different resolution -- CLIP interrogator, a button that tries to guess prompt from an image -- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway -- Batch Processing, process a group of files using img2img -- Img2img Alternative, reverse Euler method of cross attention control -- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions -- Reloading checkpoints on the fly -- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one -- [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community -- [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once - - separate prompts using uppercase `AND` - - also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2` -- No token limit for prompts (original stable diffusion lets you use up to 75 tokens) -- DeepDanbooru integration, creates danbooru style tags for anime prompts -- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args) -- via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI -- Generate forever option -- Training tab - - hypernetworks and embeddings options - - Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime) -- Clip skip -- Hypernetworks -- Loras (same as Hypernetworks but more pretty) -- A sparate 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 -- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML. -- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients)) -- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions -- [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions -- Now without any bad letters! -- Load checkpoints in safetensors format -- Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64 -- Now with a license! -- Reorder elements in the UI from settings screen -- +![](ui-screenshot.jpg) -## Installation and Running -Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs. +
-Alternatively, use online services (like Google Colab): +## Notes -- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services) +Fork is as close as up-to-date with origin as time allows +All code changes are merged upstream whenever possible -### Automatic Installation on Windows -1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH" -2. Install [git](https://git-scm.com/download/win). -3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`. -4. Place stable diffusion checkpoint (`model.ckpt`) in the `models/Stable-diffusion` directory (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it). -5. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user. +Fork adds extra functionality: +- Ships with additional **extensions** + e.g. `System Info`, `Steps Animation`, etc. +- Ships with set of **CLI** tools that rely on *SD API* for execution: + e.g. `generate`, `train`, `bench`, etc. + [Full list]() -### Automatic Installation on Linux -1. Install the dependencies: -```bash -# Debian-based: -sudo apt install wget git python3 python3-venv -# Red Hat-based: -sudo dnf install wget git python3 -# Arch-based: -sudo pacman -S wget git python3 -``` -2. To install in `/home/$(whoami)/stable-diffusion-webui/`, run: -```bash -bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh) -``` +Fork does differ in few things: -### Installation on Apple Silicon +- Additional simplified start script + > ./automatic.sh + > ./secure.sh + + Use `secure.sh` if you want to startup with username/password auth enabled and listen on global IP + Existing `webui.sh` still exists for fresh installs to auto-install dependencies, etc. +- Additional simplified install script + > ./install.sh +- Drops compatibility with `python` **3.7** and requires **3.10** +- Updated **Python** libraries to latest known compatible versions + e.g. `accelerate`, `transformers`, `numpy`, etc. +- Includes opinionated **System** and **Options** configuration + e.g. `samplers`, `upscalers`, etc. +- Includes reskinned **UI** + Black and orange dark theme with fixed width options panels and larger previews +- Includes **SD2** configuration files +- Uses simplified folder structure + e.g. `/train`, `/outputs/*` +- Modified training templates -Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon). +Only Python library which is not auto-updated is `PyTorch` itself as that is very system specific +For some Torch optimizations notes, see Wiki -## Contributing -Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing) +Fork is compatible with regular **PyTorch 1.13** as well as pre-release of **PyTorch 2.0** +See [Wiki](https://github.com/vladmandic/automatic/wiki) for **Torch** optimization notes -## Documentation -The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki). -## Credits -Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file. +
-- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers -- 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 -- LDSR - https://github.com/Hafiidz/latent-diffusion -- MiDaS - https://github.com/isl-org/MiDaS -- Ideas for optimizations - https://github.com/basujindal/stable-diffusion -- Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing. -- Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion) -- Sub-quadratic Cross Attention layer optimization - Alex Birch (https://github.com/Birch-san/diffusers/pull/1), Amin Rezaei (https://github.com/AminRezaei0x443/memory-efficient-attention) -- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas). -- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd -- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot -- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator -- Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch -- xformers - https://github.com/facebookresearch/xformers -- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru -- Security advice - RyotaK -- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user. -- (You) +## Docs + +Everything is in [Wiki](https://github.com/vladmandic/automatic/wiki) +Except my current [TODO](TODO.md) diff --git a/config.json b/config.json index bf471c9b0..d566e01ec 100644 --- a/config.json +++ b/config.json @@ -60,7 +60,7 @@ "training_enable_tensorboard": true, "training_tensorboard_save_images": false, "training_tensorboard_flush_every": 120, - "sd_model_checkpoint": "zeipher-f222.ckpt [9e2c6ceff3]", + "sd_model_checkpoint": "sd-v15-runwayml.ckpt [cc6cb27103]", "sd_checkpoint_cache": 0, "sd_vae_checkpoint_cache": 0, "sd_vae": "vae-ft-mse-840000-ema-pruned.ckpt", @@ -144,7 +144,7 @@ "ScuNET", "roll-artist" ], - "sd_checkpoint_hash": "9e2c6ceff3f6d6f65c6fb0e10d8e69d772871813be647fd2ea5d06e00db33c1f", + "sd_checkpoint_hash": "cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516", "ldsr_steps": 100, "ldsr_cached": false, "SWIN_tile": 192, diff --git a/extensions-builtin/sd-extension-steps-animation b/extensions-builtin/sd-extension-steps-animation index cac3e3d00..ed53dc0ed 160000 --- a/extensions-builtin/sd-extension-steps-animation +++ b/extensions-builtin/sd-extension-steps-animation @@ -1 +1 @@ -Subproject commit cac3e3d0024290cb85f2713c169cf3b20d289b54 +Subproject commit ed53dc0ed2c4547d3629d7712908eb0189bc48bd diff --git a/modules/shared.py b/modules/shared.py index cd78e50a4..efd476604 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -35,7 +35,7 @@ parser.add_argument("--no-half-vae", action='store_true', help="do not switch th 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(script_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("--textual-inversion-templates-dir", type=str, default=os.path.join(script_path, 'train/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("--allow-code", action='store_true', help="allow custom script execution from webui") diff --git a/wiki b/wiki index 457d67ce5..de8c64443 160000 --- a/wiki +++ b/wiki @@ -1 +1 @@ -Subproject commit 457d67ce561d3943a49d6b33289628e84bcd757c +Subproject commit de8c644430c8228c4e408cab35494ce610f8162d