Framework
Diffusers
Diffusers is an open-source AI framework from Hugging Face, launched in 2022, made for developers.
A PyTorch library of pretrained diffusion pipelines for generating images, video and audio.
Main jobs: Text to image. It is open source and free to use. You can use it on your own server, offline on your own machine and through an API.
Markdown version of https://godooo.ai/en/framework/diffusers. Every page on this site has one: add .md to its address.
At a glance
- Type
- Framework
- Made by
- Hugging Face
- Launched
- 2022
- Galaxy
- Image
- Open source
- Yes · Apache-2.0
- Source code
- github.com/huggingface/diffusers
- GitHub stars
- 34,595
- How you run it
- Self-host · Runs offline · API
- Made for
- Developers
- Website
- huggingface.co
What it can do
Text to imagemain jobunconfirmed
“Diffusers is a library of state-of-the-art pretrained diffusion models for generating videos, images, and audio.”— huggingface.co, 2026-09-24
Image editingsupportedunconfirmed
“Text-guided Image-to-Image ControlNet lllyasviel/sd-controlnet-canny Text-guided Image-to-Image InstructPix2Pix timbrooks/instruct-pix2pix”— github.com, 2026-09-24
Model trainingsupportedunconfirmed
“Whether you're looking for a simple inference solution or training your own diffusion models, 🤗 Diffusers is a modular toolbox that supports both.”— github.com, 2026-09-24
Text to videosupportedunconfirmed
“Diffusers is a library of state-of-the-art pretrained diffusion models for generating videos, images, and audio.”— huggingface.co, 2026-09-24
Upscaling and enhancementsupportedunconfirmed
“Super Resolution Stable Diffusion Upscale stabilityai/stable-diffusion-x4-upscaler”— github.com, 2026-09-24
unconfirmedproposed by a machine, awaiting calibration
Alternatives
- Jimeng 即梦Free plan + paid upgradesAlso does: Text to image, Text to video, Image editing; no code needed
- KreaFree plan + paid upgradesAlso does: Text to image, Upscaling and enhancement, Image editing; no code needed
- Stable Diffusion WebUIOpen source, freeAlso does: Image editing, Text to image, Upscaling and enhancement; no code needed
- InvokeOpen source, freeAlso does: Image editing, Text to image, Upscaling and enhancement; no code needed
- Adobe FireflyFree plan + paid upgradesAlso does: Text to image, Image editing, Text to video; no code needed
- ComfyUIOpen source, freeAlso does: Text to image, Text to video, Upscaling and enhancement; no code needed
- Nano BananaAlso does: Image editing, Text to image; no code needed
- FooocusOpen source, freeAlso does: Text to image, Image editing, Upscaling and enhancement; no code needed
- Leonardo.AiFree plan + paid upgradesAlso does: Text to image, Image editing, Upscaling and enhancement; no code needed
- MidjourneyPaidAlso does: Text to image, Image editing; no code needed
- DALL·EAlso does: Text to image, Image editing; no code needed
- FLUXOpen source, freeAlso does: Text to image, Image editing; no code needed
Connections
- Applies
- Diffusion Model
- Built with
- PyTorch
Questions
What is Diffusers?
Diffusers is an open-source AI framework from Hugging Face, launched in 2022, made for developers. A PyTorch library of pretrained diffusion pipelines for generating images, video and audio.
Is Diffusers free?
Yes. Diffusers is open source (Apache-2.0) and free to use.
Is Diffusers open source?
Yes, under the Apache-2.0 license. The source code is at https://github.com/huggingface/diffusers.
Can Diffusers run locally?
Yes. Diffusers can run offline on your own machine. It can also be self-hosted on your own server.
What can Diffusers do?
Main jobs: Text to image. It can also do: Image editing, Model training, Text to video, Upscaling and enhancement.
Who makes Diffusers?
Diffusers is made by Hugging Face.
What are open-source alternatives to Diffusers?
Open-source ones: Stable Diffusion WebUI, Invoke, ComfyUI, Fooocus and FLUX. Others: Jimeng 即梦, Krea, Adobe Firefly, Nano Banana, Leonardo.Ai and Midjourney.
Sources
- huggingface.co/docs/diffusers/indexchecked 2026-09-24
- github.com/huggingface/diffuserschecked 2026-09-24
- huggingface.co/docs/diffusers