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 supported16 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Memory Management Regression in ComfyUI (Update 13)
- Partially enabled FP16 reasoning in the Qwen Image Models
- nano banana pro - generating images are full black - no image generated
- feat: Add audio_cover_strength input to ACEStep 1.5 text encoder node
- feat: add route to automatically download missing models
- ComfyUI using more memory and crashing after upgrading GPU.
- Fix MPS upscale/VAE failures: enforce contiguous tiled input and safer split-attention chunking
- Save Image / Preview Image (Node 2.0) stops updating after opening & closing a new empty workflow tab (UI shows stale image)
- ComfyUI Desktop - ComfyUI and python processes do not shut down when closing the app
- Allow graph expansion nodes to return lists and handle OUTPUT_IS_LIST correctly
- Docs
- Python not yet supported