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
- Multi-GPU non-CUDA: unconditional torch.cuda.set_device() in worksplit-multigpu hot paths
- ComfyUI fails to cache model to RAM, reloads from disk every run.
- CheckpointSave fails with FakeDevice when Dynamic VRAM is enabled
- Microsoft Lens - Turbo, Base, Regular - Image model
- Please support new video model "LongCat-Video-Avatar-1.5"
- set_attr_param re-wraps Parameter subclasses, breaking bnb Params4bit (NF4/FP4) at partially_unload
- VAE Encode with Qwen Image VAE Ignores Batched Images
- The model directory does not contain the model "vitpose-l-wholebody.onnx" or "yolov10m.onnx" that should be detected.
- allow actual COMBO in the "load image from Outputs" to inlcude TEMP folder
- After switching the workflow, the model that was switched in the previous workflow is automatically initialized.
- Docs
- Python not yet supported