Spaces:
Runtime error
Runtime error
Update README.md
Browse files
README.md
CHANGED
@@ -1,161 +1,9 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
- Outpainting
|
11 |
-
- Inpainting
|
12 |
-
- Color Sketch
|
13 |
-
- Prompt Matrix
|
14 |
-
- Stable Diffusion Upscale
|
15 |
-
- Attention, specify parts of text that the model should pay more attention to
|
16 |
-
- a man in a ((tuxedo)) - will pay more attention to tuxedo
|
17 |
-
- a man in a (tuxedo:1.21) - alternative syntax
|
18 |
-
- select text and press ctrl+up or ctrl+down to automatically adjust attention to selected text (code contributed by anonymous user)
|
19 |
-
- Loopback, run img2img processing multiple times
|
20 |
-
- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
|
21 |
-
- Textual Inversion
|
22 |
-
- have as many embeddings as you want and use any names you like for them
|
23 |
-
- use multiple embeddings with different numbers of vectors per token
|
24 |
-
- works with half precision floating point numbers
|
25 |
-
- train embeddings on 8GB (also reports of 6GB working)
|
26 |
-
- Extras tab with:
|
27 |
-
- GFPGAN, neural network that fixes faces
|
28 |
-
- CodeFormer, face restoration tool as an alternative to GFPGAN
|
29 |
-
- RealESRGAN, neural network upscaler
|
30 |
-
- ESRGAN, neural network upscaler with a lot of third party models
|
31 |
-
- SwinIR and Swin2SR([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
|
32 |
-
- LDSR, Latent diffusion super resolution upscaling
|
33 |
-
- Resizing aspect ratio options
|
34 |
-
- Sampling method selection
|
35 |
-
- Adjust sampler eta values (noise multiplier)
|
36 |
-
- More advanced noise setting options
|
37 |
-
- Interrupt processing at any time
|
38 |
-
- 4GB video card support (also reports of 2GB working)
|
39 |
-
- Correct seeds for batches
|
40 |
-
- Live prompt token length validation
|
41 |
-
- Generation parameters
|
42 |
-
- parameters you used to generate images are saved with that image
|
43 |
-
- in PNG chunks for PNG, in EXIF for JPEG
|
44 |
-
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
|
45 |
-
- can be disabled in settings
|
46 |
-
- drag and drop an image/text-parameters to promptbox
|
47 |
-
- Read Generation Parameters Button, loads parameters in promptbox to UI
|
48 |
-
- Settings page
|
49 |
-
- Running arbitrary python code from UI (must run with --allow-code to enable)
|
50 |
-
- Mouseover hints for most UI elements
|
51 |
-
- Possible to change defaults/mix/max/step values for UI elements via text config
|
52 |
-
- Tiling support, a checkbox to create images that can be tiled like textures
|
53 |
-
- Progress bar and live image generation preview
|
54 |
-
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
|
55 |
-
- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
|
56 |
-
- Styles, a way to save part of prompt and easily apply them via dropdown later
|
57 |
-
- Variations, a way to generate same image but with tiny differences
|
58 |
-
- Seed resizing, a way to generate same image but at slightly different resolution
|
59 |
-
- CLIP interrogator, a button that tries to guess prompt from an image
|
60 |
-
- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
|
61 |
-
- Batch Processing, process a group of files using img2img
|
62 |
-
- Img2img Alternative, reverse Euler method of cross attention control
|
63 |
-
- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
|
64 |
-
- Reloading checkpoints on the fly
|
65 |
-
- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
|
66 |
-
- [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community
|
67 |
-
- [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once
|
68 |
-
- separate prompts using uppercase `AND`
|
69 |
-
- also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
|
70 |
-
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
|
71 |
-
- DeepDanbooru integration, creates danbooru style tags for anime prompts
|
72 |
-
- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
|
73 |
-
- via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
|
74 |
-
- Generate forever option
|
75 |
-
- Training tab
|
76 |
-
- hypernetworks and embeddings options
|
77 |
-
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
|
78 |
-
- Clip skip
|
79 |
-
- Hypernetworks
|
80 |
-
- Loras (same as Hypernetworks but more pretty)
|
81 |
-
- A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt.
|
82 |
-
- Can select to load a different VAE from settings screen
|
83 |
-
- Estimated completion time in progress bar
|
84 |
-
- API
|
85 |
-
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
|
86 |
-
- 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))
|
87 |
-
- [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
|
88 |
-
- [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
|
89 |
-
- Now without any bad letters!
|
90 |
-
- Load checkpoints in safetensors format
|
91 |
-
- Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
|
92 |
-
- Now with a license!
|
93 |
-
- Reorder elements in the UI from settings screen
|
94 |
-
-
|
95 |
-
|
96 |
-
## Installation and Running
|
97 |
-
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.
|
98 |
-
|
99 |
-
Alternatively, use online services (like Google Colab):
|
100 |
-
|
101 |
-
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
|
102 |
-
|
103 |
-
### Automatic Installation on Windows
|
104 |
-
1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"
|
105 |
-
2. Install [git](https://git-scm.com/download/win).
|
106 |
-
3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
|
107 |
-
4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
|
108 |
-
|
109 |
-
### Automatic Installation on Linux
|
110 |
-
1. Install the dependencies:
|
111 |
-
```bash
|
112 |
-
# Debian-based:
|
113 |
-
sudo apt install wget git python3 python3-venv
|
114 |
-
# Red Hat-based:
|
115 |
-
sudo dnf install wget git python3
|
116 |
-
# Arch-based:
|
117 |
-
sudo pacman -S wget git python3
|
118 |
-
```
|
119 |
-
2. To install in `/home/$(whoami)/stable-diffusion-webui/`, run:
|
120 |
-
```bash
|
121 |
-
bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)
|
122 |
-
```
|
123 |
-
3. Run `webui.sh`.
|
124 |
-
### Installation on Apple Silicon
|
125 |
-
|
126 |
-
Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
|
127 |
-
|
128 |
-
## Contributing
|
129 |
-
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
|
130 |
-
|
131 |
-
## Documentation
|
132 |
-
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
|
133 |
-
|
134 |
-
## Credits
|
135 |
-
Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
|
136 |
-
|
137 |
-
- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
|
138 |
-
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
|
139 |
-
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
|
140 |
-
- CodeFormer - https://github.com/sczhou/CodeFormer
|
141 |
-
- ESRGAN - https://github.com/xinntao/ESRGAN
|
142 |
-
- SwinIR - https://github.com/JingyunLiang/SwinIR
|
143 |
-
- Swin2SR - https://github.com/mv-lab/swin2sr
|
144 |
-
- LDSR - https://github.com/Hafiidz/latent-diffusion
|
145 |
-
- MiDaS - https://github.com/isl-org/MiDaS
|
146 |
-
- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
|
147 |
-
- Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
|
148 |
-
- Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
|
149 |
-
- 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)
|
150 |
-
- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
|
151 |
-
- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
|
152 |
-
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
|
153 |
-
- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
|
154 |
-
- Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
|
155 |
-
- xformers - https://github.com/facebookresearch/xformers
|
156 |
-
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
|
157 |
-
- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
|
158 |
-
- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
|
159 |
-
- Security advice - RyotaK
|
160 |
-
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
|
161 |
-
- (You)
|
|
|
1 |
+
license: apache-2.0
|
2 |
+
title: Automatic Stable Diffusion
|
3 |
+
sdk: gradio
|
4 |
+
sdk_version: 3.16.2
|
5 |
+
app_file: app.py
|
6 |
+
pinned: true
|
7 |
+
emoji: π
|
8 |
+
colorFrom: gray
|
9 |
+
colorTo: purple
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|