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: use resample-aware bilinear+antialias interpolation for tensor/numpy resize in VaeImageProcessor
- Fix load_lora_weights crash on modular sub-pipelines without transformer
- hooks/pyramid_attention_broadcast: remove redundant iteration==0 guard and fix stale cache VRAM leak
- diffusers-0.38.0.dev0 breaks offloading
- Fix UniPC scheduler device mismatch when using offloading
- [Neuron] Enable `torch.compile` compatibility with Neuron device
- Loading loras on "text_pipe" of a modular pipeline fails
- [attention backends] Add Neuron backend for context parallel
- Add attention mask input support for flash backend
- Fix encoder difference between modular and standard pipelines for Qwen Image and consistency with other models
- Docs
- Python not yet supported