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
- Fix NaN samples from DDPM fixed_large_log variance
- Fix nan sigmas when num_inference_steps=1 with shift_terminal
- diffusers docs have too many `cuda` hardcoding, this is unfriendly to device-agnostic
- Set scheduler begin index in remaining FlowMatch pipelines to avoid DtoH sync
- docs: correct stated defaults in Chroma pipeline docstrings
- Fix UnboundLocalError in get_parameter_dtype from a shadowed tuple builtin
- [tests] migrate acestep, auraflow, cogview4, and helios tests
- [wip][core] propagate sage attention updates.
- UnCLIPScheduler.set_timesteps crashes (ZeroDivisionError) for 1 step and silently returns an empty schedule for 0 steps
- CogVideoX: remove per-step host syncs from the denoising loop, enable regional compilation
- Docs
- Python not yet supported