diffusers
https://github.com/huggingface/diffusers
Python
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
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 supported3 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- Bump the actions group across 1 directory with 13 updates
- RoPE helpers make float32 copies of q / k on every call
- FP32LayerNorm makes two full-size float32 copies on every call
- Skip the float32 copies in FP32LayerNorm on CUDA
- Bump doc-builder to render math in docstring descriptions
- Wan transformer block makes float32 copies of hidden_states in its residual adds
- Drop the float32 copies in the Wan block residual adds
- Avoid float32 copies of q / k in the RoPE helpers
- unload_textual_inversion(token) leaves the extra tokens of a multi-vector embedding behind, so it can't be loaded again
- `_tp_plan` / `_cp_plan`: allow entries for modules that are not always present
- Docs
- Python not yet supported