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
- Unknown /upload/image type returns 500 instead of a client error
- [Partner Nodes] feat(credits): respect "X-Comfy-Credits-Used" header from the comfy-api
- Does not work as intended (Small speedup for text model sampling.#14773 )
- the PATH of offload-arch.exe is not in accord with my actual path with the Portable for AMD GPU version of ComfyUI
- 我写了关于comfyui的教程，欢迎交流I have written a tutorial about comfyui. Welcome to exchange ideas
- Please support new model from microsoft..."Mage-VL and Mage-ViT"
- We need better install instructions for limited download quota and low storage space (as there is no checks)
- [Partner Nodes] feat(Anthropic): add Claude Opus 5 model
- Black image (NaN) with int8_convrot diffusion models on gfx1201 / ROCm, but int8_convrot text encoder works fine
- Fix OFT/BOFT constraint scaling when loading lycoris models
- Docs
- Python not yet supported