Stability AI logoStability AI

Stability AI is a research company best known for its Stable Diffusion family of state of the art open source image generation models.

Stability AI models

Stability AI logoStable Diffusion 3 Medium

Image generation
3A100

Stability AI logoStable Diffusion XL

Image generation
XL 1.0A10G

Stability AI logoComfy UI

Image generation
A10G

Stability AI logoStable Video Diffusion

Image to video
Video 1.0A10G

Stability AI logoSDXL ControlNet Canny

Image generation
XL 1.0ControlNet - CannyA10G

Stability AI logoSDXL ControlNet Depth

Image generation
XL 1.0ControlNet - DepthA10G

Stability AI logoSDXL ControlNet

Image generation
XL 1.0ControlnetA10G

Stability AI logoSDXL Turbo

Image generation
XL 1.0TurboA10G

Stability AI logoStable Diffusion

Image generation
v2.1A10G

About Stability AI

Stability AI is a leading open source generative AI company best known for image generation models. Founded in 2019 and headquartered in London, Stability AI is a worldwide organization.

While Stability AI is best known for text-to-image models like Stable Diffusion, they create generative models across image and video in 2D and 3D, text and code in multiple languages, audio, and more.

What license does Stability AI release models under?

Stability AI licenses its core models via its Stability AI Membership, under which non-commercial use is free, while a commercial use license can be purchased. A Stability AI Membership is required to run these core models on Baseten for commercial purposes.

Several of Stability AI’s models were released before they created their Membership program, and are individually licensed. Stable Diffusion XL 1.0, for example, is available under a variant of an OpenRAIL license.

What does Stability AI do?

Stability AI trains models from scratch and performs original research to create category-defining open source foundation models.

What are Stability AI models used for?

Stability AI creates models for a range of tasks, from image and video generation to text generation to audio. This set of models across modalities makes Stability AI ideal for many use cases.

Can I fine tune Stability AI models?

Stability AI creates foundation models that are ideal for fine tuning. From DreamBooth for Stable Diffusion to the vast number of community-generated LoRAs available, you can find or create fine-tuned variants of Stability AI models for any project you have in mind.

Deploy any model in just a few commands

Avoid getting tangled in complex deployment processes. Deploy best-in-class open-source models and take advantage of optimized serving for your own models.

$

truss init -- example stable-diffusion-2-1-base ./my-sd-truss

$

cd ./my-sd-truss

$

export BASETEN_API_KEY=MdNmOCXc.YBtEZD0WFOYKso2A6NEQkRqTe

$

truss push

INFO

Serializing Stable Diffusion 2.1 truss.

INFO

Making contact with Baseten πŸ‘‹ πŸ‘½

INFO

πŸš€ Uploading model to Baseten πŸš€

Upload progress: 0% | | 0.00G/2.39G