Diffusers
Hugging FaceDiffusers is a PyTorch library from Hugging Face providing state-of-the-art pretrained diffusion models for generating images, audio, and 3D molecular structures. It offers ready-to-use inference pipelines, interchangeable noise schedulers, and pretrained models that serve as building blocks for custom diffusion systems. It is the de facto open source library for working with diffusion-based generative models.
Verified live 2026-06-22 via primary sources. LICENSE file is the standard, unmodified Apache 2.0 text.
Openness
5 high confidence- license
- Apache-2.0(OSI)
- source
- public
- core-gated
- ungated
LICENSE file is the standard, unmodified Apache 2.0 text.
- https://github.com/huggingface/diffusers/blob/main/LICENSE recorded 2026-06-22
Standard Apache License 2.0 full text
Adoption
4 high confidencePyPI last_month downloads of 7,406,705 fall in the 5M-50M Level 4 band.
- https://pypistats.org/api/packages/diffusers/recent recorded 2026-06-22
last_month downloads = 7,406,705
Capability
4 high confidenceDeep but domain-specific to diffusion/generative models rather than general-purpose ML.
- https://github.com/huggingface/diffusers recorded 2026-06-22
Describes pipelines, schedulers, and pretrained diffusion models
Unchanged since 2026-07-30 (last edited, not re-checked)