Files

65 lines
5.3 KiB
Markdown
Raw Permalink Normal View History

2022-08-28 13:35:40 +02:00
<EFBFBD><EFBFBD># Stable Diffusion WebUI Docker
2022-08-27 12:38:12 +01:00
2022-08-28 13:35:40 +02:00
Run Stable Diffusion on your machine with a nice UI without any hassle!
2022-08-27 12:38:12 +01:00
2022-08-28 15:27:04 +02:00
This repository provides the [WebUI](https://github.com/hlky/stable-diffusion-webui) as docker for easy setup and deployment.
2022-08-27 12:38:12 +01:00
## Setup
2022-08-27 16:28:55 +01:00
make sure you have docker installed and up to date. Download this repo and run:
2022-08-27 18:02:26 +01:00
2022-08-27 12:38:12 +01:00
```
docker compose build
```
2022-08-27 18:02:26 +01:00
2022-08-28 13:35:40 +02:00
you can let it build in the background while you download the different models
2022-08-27 12:38:12 +01:00
2022-08-28 15:27:04 +02:00
- [Stable Diffusion v1.4 (4GB)](https://drive.yerf.org/wl/?id=EBfTrmcCCUAGaQBXVIj5lJmEhjoP1tgl), rename to `model.ckpt`
- [GFPGANv1.3.pth (333MB)](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth) to improve generated faces.
- [RealESRGAN_x4plus.pth (64MB)](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth) and [RealESRGAN_x4plus_anime_6B.pth (18MB)](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth) for super-sampling.
2022-08-28 13:35:40 +02:00
Put all of the downloaded models in the `models` folder, the folder structure should look something like this:
2022-08-27 12:38:12 +01:00
```
%%% README.md
%%% docker-compose.yml
%%% build
%%% cache
%%% models
%<25><00> %%% GFPGANv1.3.pth
%<25><00> %%% RealESRGAN_x4plus.pth
%<25><00> %%% RealESRGAN_x4plus_anime_6B.pth
%<25><00> %%% model.ckpt
%%% output
```
2022-08-28 13:35:40 +02:00
## Run
2022-08-27 12:38:12 +01:00
2022-08-27 13:01:33 +01:00
After the build is done, you can run the app with:
2022-08-27 12:38:12 +01:00
```
docker compose up --build
```
2022-08-27 13:01:33 +01:00
Will start the app on http://localhost:7860/
2022-08-27 12:38:12 +01:00
Note: the first start will take sometime as some other models will be downloaded, these will be cached in the `cache` folder, so next runs are faster.
## Config
2022-08-28 18:41:54 +02:00
in the `docker-compose.yml` you can change the cli parameters of the webui, the ports, and gpu setup. You can find all cli configs [here](https://github.com/hlky/stable-diffusion-webui/blob/244f945c40b8dec3fd1faf8824b99abeb3bc4b97/webui.py)
2022-08-27 12:56:25 +01:00
# Disclaimer
The authors of this project are not responsible for any content generated using this interface.
2022-08-27 18:02:26 +01:00
This license of this software forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please read [the license](./LICENSE).
2022-08-28 15:27:04 +02:00
# Thanks
Special thanks to everyone behind these awesome projects, without them, none of this would have been possible:
- [hlky/stable-diffusion-webui](https://github.com/hlky/stable-diffusion-webui)
- [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
- [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion)
2022-08-27 12:38:12 +01:00