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 supported4 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Fix device mismatch errors Qwen 3.5 partial loading with no dynamic vram.
- qwen3.5: support flash-linear-attention.
- fix: make attention_mask optional in LTXBaseModel.forward
- Ipadapter Unified loader "Clip vision not found"
- fix: skip NaN keypoints in SDPoseDrawKeypoints to prevent ValueError
- fix: support batch broadcasting in JoinImageWithAlpha node
- Add HY-OmniWeaving support for HunyuanVideo 1.5
- SaveAnimatedWebP takes forever
- Fix torch.load missing weights_only in LoadTrainingDataset
- fix: MPS memory reporting and cache synchronization
- Docs
- Python not yet supported