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 UnboundLocalError in get_parameter_dtype from a shadowed tuple builtin
- UnCLIPScheduler.set_timesteps crashes (ZeroDivisionError) for 1 step and silently returns an empty schedule for 0 steps
- Remove per-step host syncs from the CogVideoX denoising loop, enable regional compilation
- Update remaining pipeline docstrings from `torch_dtype` to `dtype`
- fixed_large_log variance sampling returns NaNs
- fix: raise a clear error in UnCLIPScheduler.set_timesteps for fewer than 2 steps
- fix: npu_rms_norm does not support gamma=None, use all-ones tensor in…
- Cast ControlNet image columns before preprocessing
- train_lcm_distill_lora_sdxl.py: intermediate validation logs the un-adapted base model; saved LoRA mixes key conventions and drops all attention adapters on load
- Fix silent weight corruption when loading with device_map on MPS (torch < 2.13)
- Docs
- Python not yet supported