comfyui
https://github.com/comfyanonymous/comfyui
Python
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported0 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- fp8mixed.safetensors - Are there any code of how to convert a Diffusion model into Mixed FP8 which is better than Scaled FP8 right?
- Painter I2V like motion amplification in WanImageToVideo node.
- not so comfy
- 使用現代節點設計（vue節點）時，Ｋ採樣器（高級）裡的＂生成後控制＂選項消失。
- Support for loading Jpeg XL (and possibly saving as Jpeg XL)
- TAESD previews with Z-Image-Turbo cause a massive increase in VRAM usage
- Custom colors for node title bar not loading anymore after Update 0.3.75
- Removal of internal/files API breaks 3rd party tools such as GIMP plugins
- Pricing page for apis by default should show prices.
- V3 nodes COMBO widget are incompatible with older version of the UI (using the argument "--front-end-root")
- Docs
- Python not yet supported