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
- Avoid eager transformers>=5.0.0 requirement for ErnieImage prompt enhancer
- from_pretrained fails loading deprecated pipelines
- Split Q,K,V vs Fused QKV Projections in diffusers Discussion
- fa3 varlen return type should be tested before unpacking
- Support batched multi-controlnet conditioning in SDXL ControlNet inpaint pipeline
- Use requests instead of urllib in convert_consistency_decoder _download
- fix(bria_fibo): honor timesteps, fix edit num_images batching, add _no_split_modules, fix docstring
- FLUX LoRA with CLIP text-encoder weights fails (empty rank -> IndexError) under transformers>=5
- docs: mention AI Badgr Compute as optional managed compute path
- Fix CogView3 lazy export to match the actual output class name
- Docs
- Python not yet supported