Rare find

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

huggingface.co/docs/diffusers

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

June 2026
  • Fix Kohya UNet LoRA key conversion for conv_in/conv_out/time_embeddin…
  • Fix DreamLite legacy block type aliases (#14066)
  • feat: bump safetensors to 0.8.0 (#13971)
  • docs: fix repeated word typo in set_timesteps docstring (#13876)
  • multi-GPU VAE Fix for Cosmos 3 (#13924)
  • Add from_single_file support for SkyReelsV2 and ChronoEdit transforme…
  • [discrete diffusion] Add DiffusionGemma pipeline and schedulers (#13986)
  • [tests] implement base model output caching in model-level tests (#14…
  • fix(bria_fibo): fix guidance_embeds, prompt_embeds, tensor-image and …
  • fix claude code review fix in PRs. (#14058)
  • [.ai] document single-file model layout and "don't reimplement Diffus…
  • Fix model cuda tests (#13975)
  • Krea 2 LoRA DreamBooth trainer (#14046)
  • fix(flux): tighten check_inputs validation (#13955)
  • Enable BitsAndBytes quantization in MPS (#13915)
  • [.ai doc] Refine .ai attention-mask and component-mutation guidance (…
  • Add Krea 2 (K2) text-to-image pipeline and transformer (#14045)
  • [Fix] Fix three final_layer LoRA conversion bugs in _convert_sd_scrip…
  • Fix `Ideogram4MRoPE` collapsing under `torch.autocast` (compute rotar…
  • Fix LTX2 connector token/register layout (regression from #13564) (#1…