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 supported1 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- fix rope dtype from torch.float64 to torch.float32
- Accommodate custom components in `maybe_raise_or_warn`
- Ensure consistent dynamic module path for custom components
- Add hash check for dynamic modules cache
- Fix SDXL Refiner with Higher Order Schedulers
- Improve `trust_remote_code`
- Wrong default layers for Flux 2 Klein
- Support for Exclusive Self Attention (XSA) in Diffusion Models (DiT, U-Net, etc.)
- Insufficient trust check for custom_pipeline parameter of DiffusionPipeline.from_pretrained method
- [feat] JoyAI-JoyImage-Edit support
- Docs
- Python not yet supported