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 supported9 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Bernini version along with MLLM and VIT
- model_management: fix free_memory race with cleanup_models finalizer
- RuntimeError: The expanded size of the tensor (64) must match the existing size (128) at non-singleton dimension 3. Target sizes: [48, 1, 64, 64]. Tensor sizes: [16, 1, 128, 128]
- [Partner Nodes] feat(bria): add Transparent option to Remove Video Background
- we need Pixal3D
- SamplerCustomAdvanced no latent preview
- The "Download-All" button does not download anything. Nodes don't download.
- AttributeError: 'Linear' object has no attribute 'weight_scale' — ModelMergeSimple on a quantized (fp8/QuantizedTensor) model: unguarded getattr in get_key_weight vs synthetic quant state-dict keys
- ComfyUI fails to start with a `RuntimeError` due to a CUDA version mismatch between PyTorch and TorchAudio.
- TextGenerate could replace many custom nodes, but baulks at many LLMs (suspect feature request, but could be a bug)
- Docs
- Python not yet supported