salveamicus
commited on
Commit
•
c55ecde
1
Parent(s):
fa0a9c4
Update README.md
Browse files
README.md
CHANGED
@@ -3,145 +3,6 @@
|
|
3 |
---
|
4 |
# Forked from Automatic1111's webui repo [here](github.com/AUTOMATIC1111/stable-diffusion-webui)
|
5 |
|
6 |
-
# Stable Diffusion web UI
|
7 |
-
A browser interface based on Gradio library for Stable Diffusion.
|
8 |
-
|
9 |
-
![](screenshot.png)
|
10 |
-
|
11 |
-
## Features
|
12 |
-
[Detailed feature showcase with images](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features):
|
13 |
-
- Original txt2img and img2img modes
|
14 |
-
- One click install and run script (but you still must install python and git)
|
15 |
-
- Outpainting
|
16 |
-
- Inpainting
|
17 |
-
- Color Sketch
|
18 |
-
- Prompt Matrix
|
19 |
-
- Stable Diffusion Upscale
|
20 |
-
- Attention, specify parts of text that the model should pay more attention to
|
21 |
-
- a man in a `((tuxedo))` - will pay more attention to tuxedo
|
22 |
-
- a man in a `(tuxedo:1.21)` - alternative syntax
|
23 |
-
- select text and press `Ctrl+Up` or `Ctrl+Down` (or `Command+Up` or `Command+Down` if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)
|
24 |
-
- Loopback, run img2img processing multiple times
|
25 |
-
- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
|
26 |
-
- Textual Inversion
|
27 |
-
- have as many embeddings as you want and use any names you like for them
|
28 |
-
- use multiple embeddings with different numbers of vectors per token
|
29 |
-
- works with half precision floating point numbers
|
30 |
-
- train embeddings on 8GB (also reports of 6GB working)
|
31 |
-
- Extras tab with:
|
32 |
-
- GFPGAN, neural network that fixes faces
|
33 |
-
- CodeFormer, face restoration tool as an alternative to GFPGAN
|
34 |
-
- RealESRGAN, neural network upscaler
|
35 |
-
- ESRGAN, neural network upscaler with a lot of third party models
|
36 |
-
- SwinIR and Swin2SR ([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
|
37 |
-
- LDSR, Latent diffusion super resolution upscaling
|
38 |
-
- Resizing aspect ratio options
|
39 |
-
- Sampling method selection
|
40 |
-
- Adjust sampler eta values (noise multiplier)
|
41 |
-
- More advanced noise setting options
|
42 |
-
- Interrupt processing at any time
|
43 |
-
- 4GB video card support (also reports of 2GB working)
|
44 |
-
- Correct seeds for batches
|
45 |
-
- Live prompt token length validation
|
46 |
-
- Generation parameters
|
47 |
-
- parameters you used to generate images are saved with that image
|
48 |
-
- in PNG chunks for PNG, in EXIF for JPEG
|
49 |
-
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
|
50 |
-
- can be disabled in settings
|
51 |
-
- drag and drop an image/text-parameters to promptbox
|
52 |
-
- Read Generation Parameters Button, loads parameters in promptbox to UI
|
53 |
-
- Settings page
|
54 |
-
- Running arbitrary python code from UI (must run with `--allow-code` to enable)
|
55 |
-
- Mouseover hints for most UI elements
|
56 |
-
- Possible to change defaults/mix/max/step values for UI elements via text config
|
57 |
-
- Tiling support, a checkbox to create images that can be tiled like textures
|
58 |
-
- Progress bar and live image generation preview
|
59 |
-
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
|
60 |
-
- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
|
61 |
-
- Styles, a way to save part of prompt and easily apply them via dropdown later
|
62 |
-
- Variations, a way to generate same image but with tiny differences
|
63 |
-
- Seed resizing, a way to generate same image but at slightly different resolution
|
64 |
-
- CLIP interrogator, a button that tries to guess prompt from an image
|
65 |
-
- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
|
66 |
-
- Batch Processing, process a group of files using img2img
|
67 |
-
- Img2img Alternative, reverse Euler method of cross attention control
|
68 |
-
- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
|
69 |
-
- Reloading checkpoints on the fly
|
70 |
-
- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
|
71 |
-
- [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community
|
72 |
-
- [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once
|
73 |
-
- separate prompts using uppercase `AND`
|
74 |
-
- also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
|
75 |
-
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
|
76 |
-
- DeepDanbooru integration, creates danbooru style tags for anime prompts
|
77 |
-
- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add `--xformers` to commandline args)
|
78 |
-
- via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
|
79 |
-
- Generate forever option
|
80 |
-
- Training tab
|
81 |
-
- hypernetworks and embeddings options
|
82 |
-
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
|
83 |
-
- Clip skip
|
84 |
-
- Hypernetworks
|
85 |
-
- Loras (same as Hypernetworks but more pretty)
|
86 |
-
- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
|
87 |
-
- Can select to load a different VAE from settings screen
|
88 |
-
- Estimated completion time in progress bar
|
89 |
-
- API
|
90 |
-
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML
|
91 |
-
- 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))
|
92 |
-
- [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
|
93 |
-
- [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
|
94 |
-
- Now without any bad letters!
|
95 |
-
- Load checkpoints in safetensors format
|
96 |
-
- Eased resolution restriction: generated image's dimension must be a multiple of 8 rather than 64
|
97 |
-
- Now with a license!
|
98 |
-
- Reorder elements in the UI from settings screen
|
99 |
-
|
100 |
-
## Installation and Running
|
101 |
-
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for:
|
102 |
-
- [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended)
|
103 |
-
- [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
|
104 |
-
- [Intel CPUs, Intel GPUs (both integrated and discrete)](https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon) (external wiki page)
|
105 |
-
|
106 |
-
Alternatively, use online services (like Google Colab):
|
107 |
-
|
108 |
-
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
|
109 |
-
|
110 |
-
### Installation on Windows 10/11 with NVidia-GPUs using release package
|
111 |
-
1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract it's contents.
|
112 |
-
2. Run `update.bat`.
|
113 |
-
3. Run `run.bat`.
|
114 |
-
> For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs)
|
115 |
-
|
116 |
-
### Automatic Installation on Windows
|
117 |
-
1. Install [Python 3.10.6](https://www.python.org/downloads/release/python-3106/) (Newer version of Python does not support torch), checking "Add Python to PATH".
|
118 |
-
2. Install [git](https://git-scm.com/download/win).
|
119 |
-
3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
|
120 |
-
4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
|
121 |
-
|
122 |
-
### Automatic Installation on Linux
|
123 |
-
1. Install the dependencies:
|
124 |
-
```bash
|
125 |
-
# Debian-based:
|
126 |
-
sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
|
127 |
-
# Red Hat-based:
|
128 |
-
sudo dnf install wget git python3
|
129 |
-
# Arch-based:
|
130 |
-
sudo pacman -S wget git python3
|
131 |
-
```
|
132 |
-
2. Navigate to the directory you would like the webui to be installed and execute the following command:
|
133 |
-
```bash
|
134 |
-
wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
|
135 |
-
```
|
136 |
-
3. Run `webui.sh`.
|
137 |
-
4. Check `webui-user.sh` for options.
|
138 |
-
### Installation on Apple Silicon
|
139 |
-
|
140 |
-
Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
|
141 |
-
|
142 |
-
## Contributing
|
143 |
-
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
|
144 |
-
|
145 |
## Documentation
|
146 |
|
147 |
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
|
|
|
3 |
---
|
4 |
# Forked from Automatic1111's webui repo [here](github.com/AUTOMATIC1111/stable-diffusion-webui)
|
5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
## Documentation
|
7 |
|
8 |
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
|