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 supported21 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Support SenseNova thinking and interleaved generation
- WebSocket reconnect can unregister the replacement client
- The CLIP input is missing or invalid. Check the connected checkpoint or CLIP loader.
- Fix: Respect --lowvram and --novram on Apple Silicon (MPS)
- fix(model_management): set current CUDA device when loading multi-GPU model clones
- Add date-based output folders
- ROCm / Strix Halo (gfx1151): HIPBLAS_STATUS_ALLOC_FAILED in torch.linalg.solve during UV Unwrap (parameterize.py)
- Browser window cannot be minimized when using ComfyUI on Microsoft Edge
- Trellis2 PixelArtistry_Pixal3D_native PostProcessing > Remesh Mesh to a Small Image, Out of Memory
- Declare dtype on the VideoPositionEmb.generate_embeddings stub
- Docs
- Python not yet supported