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 FlashAttention varlen log-sum-exp return
- Per-token FlowMatch Euler steps use the opposite velocity sign
- Fix `Flux2ImageProcessor.apply_overlay` with `padding_mask_crop`
- fix(schedulers): preserve float32 timesteps when use_flow_sigmas=True
- HookRegistry.remove_hook drops the next hook's new_forward (breaks FirstBlockCache with group offloading)
- FLEX attention silently ignores is_causal=True when no mask is supplied
- fix(schedulers): LMS multistep order must ramp from 1 after set_begin_index
- [core] move pipeline-level model components to appropriate models.
- Fix is_causal being ignored by the FLEX attention backend
- fix(training): guard EMA updates on skipped optimizer step with AMP
- Docs
- Python not yet supported