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 supported24 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Multiple Concurrent Workflows - Candidate 1 - Part 1
- KSmpler Advanced A failed
- Windows: web UI hangs after ~2h (Proactor self-pipe WinError 121) and after rapid asset browsing (native sendfile)
- TRELLIS.2 texture bake fails under --bf16-vae: BakeTextureFromVoxel 'Got unsupported ScalarType BFloat16'
- MoGe-3 output is nondeterministic on CUDA: sparse_pool3d_mean sums with float index_add_ (atomics)
- Full PC freezes/BSOD during SDXL generation — RTX 3060 8 GB, NVIDIA 0x116
- Sub-quadratic attention is ~10x slower on long sequences on RDNA2 (gfx1030) because the key passed to bmm is non-contiguous
- Fix bfloat16 voxel texture baking
- 'ModelSamplingAdvanced' object has no attribute 'audio_scale'
- After the update, the new chroma_subsampling option in Create Video will break most existing related workflows.
- Docs
- Python not yet supported