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: handle CLIP text_model prefix change in transformers>=5 for FLUX LoRA loading
- `HookRegistry._child_registries_cache` goes stale after `enable_cache`/`disable_cache` → `ValueError: No context is set`
- Fix group offloading for quanto-quantized models
- [TPU] Initial TorchTPU backend integration (eager + torch.compile)
- Fix typos missed by #13842 (docs + a few additional pipelines)
- attention dispatcher assumes wrong attributes for flash attn kernel from hub
- fix(attention_dispatch): use correct attr names for FLASH_VARLEN_HUB …
- MagCache on Wan 2.2 Dual-Transformer Pipelines: Incorrect Step Accounting and Limited Effectiveness on a 4-Step Distilled Model (e.g. Wan2.2)
- Support Original Checkpoint-Compatible PEFT Adapters
- PixArtSigmaPipeline: no LoRA loading support
- Docs
- Python not yet supported