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
- 圖中三人脫衣坐愛接吻
- Corruption to widget values on subgraph flatten when widget-input boundary has no parent-side instance, resulting in incorrect widget-value offset
- Allow using float fps for LTXVEmptyLatentAudio
- fix(server): return 400 for unknown /upload/image type instead of 500
- Fix mask ndim handling in QwenImageDiffsynthControlnet.
- Mess with stable versions
- Fix lazy V3 dynamic input scheduling
- model_patcher: preserve lazy weights when saving
- [Partner Nodes] feat(Recraft): add V4.1 models and V4 image edit nodes
- Image mask output is weird in all workflows
- Docs
- Python not yet supported