Diffusers

license

Apache-2.0(OSI)

source

public

core features withheld

no

The LICENSE file is the standard, unmodified Apache 2.0 text. The repository is public and the README describes the whole library with no paid, enterprise or hosted tier beside it, so the source is public and the core ungated.

• https://cdn.jsdelivr.net/gh/huggingface/diffusers@main/LICENSE recorded 2026-09-29

  LICENSE is the Apache License text, headed "Apache License" and "Version 2.0, January 2004".

• https://cdn.jsdelivr.net/gh/huggingface/diffusers@main/README.md recorded 2026-09-29

  README header reads "Licensed under the Apache License, Version 2.0" and the file is served from the public huggingface/diffusers repository.

• https://cdn.jsdelivr.net/gh/huggingface/diffusers@main/README.md recorded 2026-09-29

  README says "Diffusers offers three core components": pipelines, schedulers and pretrained models. Searched the body for enterprise, paid, pricing, subscription, license key, hosted, self-host and on-prem: none.

• https://github.com/huggingface/diffusers/blob/main/LICENSE recorded 2026-08-13

  LICENSE file is the verbatim Apache License Version 2.0 text

• https://pypi.org/pypi/diffusers/json recorded 2026-09-29

  PyPI metadata lists "License :: OSI Approved :: Apache Software License" for the diffusers package.

Adoption is measured as PyPI downloads of the diffusers package in the trailing 30 days.

• https://pypistats.org/api/packages/diffusers/recent recorded 2026-08-13

  last_month downloads = 8,248,209 for diffusers

Diffusers covers image, video, audio and 3D generation through ready-made pipelines, interchangeable schedulers and pretrained models, plus memory optimizations such as offloading and quantization. It is deep but specific to diffusion and generative models rather than general-purpose machine learning.

• https://cdn.jsdelivr.net/gh/huggingface/diffusers@main/README.md recorded 2026-09-29

  README says "Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules" and lists pipelines, schedulers and pretrained models as its three core components.

• https://github.com/huggingface/diffusers recorded 2026-08-13

  README still describes pipelines, interchangeable schedulers and pretrained diffusion models for image, audio and 3D generation

• https://huggingface.co/docs/diffusers/index recorded 2026-09-29

  Docs home says "Diffusers is a library of state-of-the-art pretrained diffusion models for generating videos, images, and audio." and lists "offloading and quantization" optimizations and torch.compile support.