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 supported7 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- fix(directml): correct VRAM detection + make torchaudio imports optional
- AutoGrow + MatchType + allowed_types on a custom node makes invalid connections
- Protect ComfyUI from AI slop PRs
- Pixel Space Flux-klein based on Asymmetric Flow
- Clicking Download or Download All for missing models NOT working
- fix: handle LTX audio VAE dtype/device boundaries with --bf16-vae
- Seedance API sensitive-content failures should not abort concurrent task batches
- ComfyUI 0.21.1 + HiDream O1 Error
- LTX-2.3 official I2V workflow fails with SamplerCustomAdvanced tensor size mismatch.
- Starting from ComfyUI 0.21.0, dragging an image into the interface no longer loads the workflow. I would like to revert to the original behavior where dragging an image automatically loads the workflow.
- Docs
- Python not yet supported