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 supported11 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- 'CLIPTextModel' object has no attribute 'generate'
- qwen3.5: support flash-linear-attention.
- Ipadapter Unified loader "Clip vision not found"
- Add HY-OmniWeaving support for HunyuanVideo 1.5
- SaveAnimatedWebP takes forever
- Fix torch.load missing weights_only in LoadTrainingDataset
- Twinflow-Z-Image Turbo support (CORE-196)
- Mask editor : adds five basic colors <red, green, blue, white, and black> to make color selection more convenient.
- Wan 2.2 default workflow – CFG input disconnects from KSampler on load (No link found in parent graph for id [129:85] slot [7] cfg)
- Windows fatal exception: access violation : Exception Code: 0xC0000005—the classic memory access violation.
- Docs
- Python not yet supported