docker.images/stable.diffusion.webui/README.md

68 lines
1.4 KiB
Markdown

# Stable Diffusion web UI
![UI-Example](https://github.com/AUTOMATIC1111/stable-diffusion-webui/raw/master/screenshot.png)
source: https://github.com/AUTOMATIC1111/stable-diffusion-webui
## Installation
source: https://github.com/AUTOMATIC1111/stable-diffusion-webui#installation-and-running
### Automatic Installation on Windows
Install Python 3.10.6 (Newer version of Python does not support torch), checking "Add Python to PATH".
Install git.
Download the stable-diffusion-webui repository, for example by running git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git.
Run webui-user.bat from Windows Explorer as normal, non-administrator, user.
### Automatic installation on Linux
install dependencies:
```bash
pacman -S python3 python3-venv git
```
execute this command:
```bash
wget -LO ./webui.sh https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh;
chmod +x ./webui.sh;
```
run downloaded (for CPU) script:
```bash
./webui.sh --skip-torch-cuda-test --use-cpu all --share
```
Check `webui-user.sh` options
## Throubleshoting
### `no space left on device` diring pip installation
you can solve that easily:
```bash
mkdir ~/.pip.tmp;
export TMPDIR=$HOME/.pip.tmp;
```
after installation delete this directory and set this variable to default.
(check default value on your instance, it should be reset when reboot)
```
rm -r ~/.pip.tmp
```