stable-diffusion-webui/README.md

# Stable Diffusion web UI
A browser interface based on Gradio library for Stable Diffusion.

![](txt2img_Screenshot.png)

Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) wiki page for extra scripts developed by users.

## 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
- Prompt matrix
- Stable Diffusion upscale
- Attention
- Loopback
- X/Y plot
- Textual Inversion
- 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 with a lot of third party models
    - SwinIR, neural network upscaler
    - LDSR, Latent diffusion super resolution upscaling
- Resizing aspect ratio options
- Sampling method selection
- Interrupt processing at any time
- 4GB video card support
- Correct seeds for batches
- Prompt length validation
- Generation parameters added as text to PNG
- Tab to view an existing picture's generation parameters
- Settings page
- Running custom code from UI
- Mouseover hints for most UI elements
- Possible to change defaults/mix/max/step values for UI elements via text config
- Random artist button
- Tiling support: UI checkbox to create images that can be tiled like textures
- Progress bar and live image generation preview
- Negative prompt
- Styles
- Variations
- Seed resizing
- CLIP interrogator
- Prompt Editing
- Batch Processing
- Img2img Alternative
- Highres Fix
- LDSR Upscaling

## 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 Google Colab:

- [Colab, maintained by Akaibu](https://colab.research.google.com/drive/1kw3egmSn-KgWsikYvOMjJkVDsPLjEMzl)
- [Colab, original by me, outdated](https://colab.research.google.com/drive/1Iy-xW9t1-OQWhb0hNxueGij8phCyluOh).

### 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 `model.ckpt` in the `models` directory (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
5. _*(Optional)*_ Place `GFPGANv1.4.pth` in the base directory, alongside `webui.py` (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
6. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.

### 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)
```

### Installation on Apple Silicon

Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).

## Contributing
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)

## Documentation
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).

## Credits
- 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
- LDSR - https://github.com/Hafiidz/latent-diffusion
- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
- Doggettx - Cross Attention layer optimization - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
- 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
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)
first 2022-08-22 22:15:46 +08:00			`# Stable Diffusion web UI`
			`A browser interface based on Gradio library for Stable Diffusion.`

Update README.md 2022-09-24 08:22:02 +08:00			`![](txt2img_Screenshot.png)`
moved images to 2022-09-04 18:08:06 +08:00
add advertisement for custom scripts to readme 2022-09-30 13:18:05 +08:00			`Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) wiki page for extra scripts developed by users.`

Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`## Features`
			`[Detailed feature showcase with images](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features):`
moved images to 2022-09-04 18:08:06 +08:00			`- Original txt2img and img2img modes`
Removed mention of CUDA in the README The requirement to install CUDA was removed with https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/e92d4cf7476f1897fce376916dfb40755ea7920f#diff-b335630551682c19a781afebcf4d07bf978fb1f8ac04c6bf87428ed5106870f5L63 so that mention in README should be superfluous 2022-09-09 16:39:41 +08:00			`- One click install and run script (but you still must install python and git)`
moved images to 2022-09-04 18:08:06 +08:00			`- Outpainting`
			`- Inpainting`
			`- Prompt matrix`
			`- Stable Diffusion upscale`
			`- Attention`
			`- Loopback`
			`- X/Y plot`
			`- Textual Inversion`
ESRGAN support 2022-09-04 23:54:12 +08:00			`- Extras tab with:`
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`- GFPGAN, neural network that fixes faces`
			`- CodeFormer, face restoration tool as an alternative to GFPGAN`
			`- RealESRGAN, neural network upscaler`
			`- ESRGAN, neural network with a lot of third party models`
Update README.md Added SwinIR and new features to readme 2022-09-22 04:58:41 +08:00			`- SwinIR, neural network upscaler`
Update README.md 2022-09-22 06:53:35 +08:00			`- LDSR, Latent diffusion super resolution upscaling`
ESRGAN support 2022-09-04 23:54:12 +08:00			`- Resizing aspect ratio options`
moved images to 2022-09-04 18:08:06 +08:00			`- Sampling method selection`
			`- Interrupt processing at any time`
Fix multiple grammar & spelling errors in ReadMe 2022-09-13 08:00:40 +08:00			`- 4GB video card support`
moved images to 2022-09-04 18:08:06 +08:00			`- Correct seeds for batches`
			`- Prompt length validation`
			`- Generation parameters added as text to PNG`
			`- Tab to view an existing picture's generation parameters`
			`- Settings page`
			`- Running custom code from UI`
Fix multiple grammar & spelling errors in ReadMe 2022-09-13 08:00:40 +08:00			`- Mouseover hints for most UI elements`
added UI config file: ui-config.json 2022-09-04 18:52:01 +08:00			`- Possible to change defaults/mix/max/step values for UI elements via text config`
fix for live progress breaking lowvram and medvram optimizations 2022-09-07 04:10:12 +08:00			`- Random artist button`
			`- Tiling support: UI checkbox to create images that can be tiled like textures`
			`- Progress bar and live image generation preview`
enabled negative prompt by default fixed broken empty directory when prompt does not start withl etter 2022-09-10 20:41:29 +08:00			`- Negative prompt`
changed <p> to <br> in info field to prevent double line breaks when copying added new features to the list. 2022-09-10 19:53:38 +08:00			`- Styles`
			`- Variations`
			`- Seed resizing`
CLIP interrogator 2022-09-11 23:48:36 +08:00			`- CLIP interrogator`
add prompt editing to readme 2022-09-15 20:54:11 +08:00			`- Prompt Editing`
Update README.md Added SwinIR and new features to readme 2022-09-22 04:58:41 +08:00			`- Batch Processing`
			`- Img2img Alternative`
			`- Highres Fix`
Update README.md 2022-09-22 05:07:18 +08:00			`- LDSR Upscaling`
moved images to 2022-09-04 18:08:06 +08:00
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`## 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.`
let me tell you about realesrgan 2022-09-11 17:13:26 +08:00
upgrade to gradio==3.4b3 t fixthe inpain bugs rework progressbar/preview to work with new gradio remove unnecessary create style button added link to alternative colab 2022-09-24 01:46:02 +08:00			`Alternatively, use Google Colab:`

removed some information that its owner decided he did not want to share 2022-09-24 01:55:54 +08:00			`- [Colab, maintained by Akaibu](https://colab.research.google.com/drive/1kw3egmSn-KgWsikYvOMjJkVDsPLjEMzl)`
upgrade to gradio==3.4b3 t fixthe inpain bugs rework progressbar/preview to work with new gradio remove unnecessary create style button added link to alternative colab 2022-09-24 01:46:02 +08:00			`- [Colab, original by me, outdated](https://colab.research.google.com/drive/1Iy-xW9t1-OQWhb0hNxueGij8phCyluOh).`
bat file for installing and launching 2022-09-02 14:49:35 +08:00
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`### 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`.
add info about where to get models to instructions. 2022-09-18 14:09:10 +08:00			4. Place `model.ckpt` in the `models` directory (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
Update README.md 2022-09-20 00:24:58 +08:00			5. _(Optional)_ Place `GFPGANv1.4.pth` in the base directory, alongside `webui.py` (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
add info about where to get models to instructions. 2022-09-18 14:09:10 +08:00			6. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
brought manual instructions up to date reworked launching with different parameters 2022-09-09 13:37:19 +08:00
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`### Automatic Installation on Linux`
			`1. Install the dependencies:`
			```bash
			`# Debian-based:`
install/launch scripts for linux 2022-09-13 21:28:04 +08:00			`sudo apt install wget git python3 python3-venv`
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`# Red Hat-based:`
install/launch scripts for linux 2022-09-13 21:28:04 +08:00			`sudo dnf install wget git python3`
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`# Arch-based:`
			`sudo pacman -S wget git python3`
install/launch scripts for linux 2022-09-13 21:28:04 +08:00			```
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			2. To install in `/home/$(whoami)/stable-diffusion-webui/`, run:
put manual instructions above WSL, clarify they work for windows and linux 2022-09-10 05:31:58 +08:00			```bash
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)`
put manual instructions above WSL, clarify they work for windows and linux 2022-09-10 05:31:58 +08:00			```

Update README to link to wiki page for Apple Silicon installs 2022-09-22 17:35:12 +08:00			`### Installation on Apple Silicon`

			`Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).`

added contributing to readme 2022-09-30 16:57:19 +08:00			`## Contributing`
			`Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)`

Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`## Documentation`
			`The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).`
initial work on img2imgalt 2022-09-12 06:55:34 +08:00
added credits section 2022-09-05 00:09:00 +08:00			`## Credits`
			`- 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`
Added CodeFormer to Credits request from Shangchen Zhou 2022-09-21 15:38:06 +08:00			`- CodeFormer - https://github.com/sczhou/CodeFormer`
added credits section 2022-09-05 00:09:00 +08:00			`- ESRGAN - https://github.com/xinntao/ESRGAN`
Update README.md Added SwinIR and new features to readme 2022-09-22 04:58:41 +08:00			`- SwinIR - https://github.com/JingyunLiang/SwinIR`
Update README.md 2022-09-22 06:53:35 +08:00			`- LDSR - https://github.com/Hafiidz/latent-diffusion`
Update to cross attention from https://github.com/Doggettx/stable-diffusion #219 2022-09-10 17:06:19 +08:00			`- Ideas for optimizations - https://github.com/basujindal/stable-diffusion`
add prompt editing to readme 2022-09-15 20:54:11 +08:00			`- Doggettx - Cross Attention layer optimization - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.`
added credits section 2022-09-05 00:09:00 +08:00			`- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd`
added Noise generation for outpainting mk2 to credits 2022-09-17 04:17:10 +08:00			`- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot`
CLIP interrogator 2022-09-11 23:48:36 +08:00			`- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator`
added credits section 2022-09-05 00:09:00 +08:00			`- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.`
Rewrote a large portion of the README to point towards the wiki. 2022-09-15 18:50:55 +08:00			`- (You)`