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 supported24 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- SAM3: moving the text encoder with "Select CLIP Device" fails with 'NoneType' object has no attribute 'keys'
- LTXVPreprocess crashes on 4-channel (RGBA) images
- Select Model Device forces float16 on FP8 models that do not support it (Qwen Image Edit → black image)
- Cyrillic characters are replaced with .notdef glyph
- Fix various nodes that incidentally prune extra keys from latent
- feat: opt-in benchmark capture in the execution engine
- Make Math Expression value inputs optional
- [Asset] Sort options and Type filter
- WanAnimate2ToVideo produces an all-zero latent (uniform gray video) while a plain Wan T2V graph with the same checkpoint works
- Fix no-store cache header for .mjs files
- Docs
- Python not yet supported