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 supported19 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Retain dynamic model RAM cache during model loads
- Add browsable API documentation with OpenAPI spec viewer
- fix(model_detection): guard state_dict key access and support quantized tensor shapes for MiniMax H3
- refactor: fuse rms_adaln kernel and vectorize segment modulation in MiniMaxH3
- feat: add VideoTrim and VideoCrop nodes with VIDEO_EDIT widget inputs
- Trying to run Comfyui on my Computer（3060ti） text-to-image
- Fix H2D copy in SymmetricPatchifier blocking CUDA graph capture
- Fix MiniMax H3 per-step host syncs in _forward
- Fix MiniMax H3 tiled VAE decode producing a grid of mismatched tiles
- MiniMax H3: plain bf16 checkpoints (full and pruned) sample to 100% black frames on v0.32.0; int8_convrot repacks of the same weights work
- Docs
- Python not yet supported