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
- Chunk CLIP vision encoding to bound VRAM usage
- CUDA error: operation not supported
- Add native state constructors and bounded GGUF storage/output
- Add host GGML operations and lazy model patching
- Add IQ ternary and FP4 GGML compatibility kernels
- Load Audio rejects standard unsigned 8-bit PCM WAV files
- gemma4 (LTX-2.5) text encoder crashes with hipErrorProfilerNotInitialized on gfx1151 / ROCm 10.1 - all SDPA backends
- install from "Please enter the URL of the Git repository to install" is broken
- YuE2 AR stage memory explosion past ~4096 tokens on Apple Silicon (MPS) — regression in v0.40.x+
- LTX, slowdowns and aimdo memory compile error: could not start recording error
- Docs
- Python not yet supported