https://github.com/jannchie/simple-diffusion
Stable Diffusion Web UI without Web UI
https://github.com/jannchie/simple-diffusion
Last synced: 4 months ago
JSON representation
Stable Diffusion Web UI without Web UI
- Host: GitHub
- URL: https://github.com/jannchie/simple-diffusion
- Owner: Jannchie
- Created: 2024-06-09T15:26:49.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-27T03:47:48.000Z (over 1 year ago)
- Last Synced: 2025-03-19T08:53:39.381Z (about 1 year ago)
- Language: Python
- Size: 6.08 MB
- Stars: 2
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
The implementation of the stable diffusion Web UI is more efficient than diffusers. I like its rich features, but the library mixes UI, API, and other logic, making it very complex. For learning purposes, I want to extract its core generation logic and separate it from the UI and API components.
I didn't use the Web UI directly; instead, I used Web UI Forge. This is because I wanted to understand its patcher methodology (maybe from ComfyUI), which appears to provide better extensibility for the models.
For test:
``` bash
python ./simplediffusion/__init__.py
```
Coverage:
``` bash
coverage run .\simplediffusion\__init__.py; coverage xml
```
Roadmap:
- [x] Stable Diffusion XL Support
- [x] Basic text to image
- [x] Basic image to image
- [x] Reference only
- [x] ControlNet
- [ ] Other forge built-in extensions
- [ ] Stable Diffusion 3 Support