Models

Stable Diffusion

Get involved with the fastest growing open software project. Download and join other developers in creating incredible applications with Stable Diffusion as a foundation model.

Stable Audio

Generate music and sound effects in high quality using cutting-edge audio diffusion technology.

Stable LM

Experience cutting edge open access language models. Our Language researchers innovate rapidly and release open models that rank amongst the best in the industry.

Follow our journey

Sign up with your email address to receive news and updates.

Stable Audio

Use generative AI to create music and sound effects.

Stable Audio is Stability AI’s first product for music and sound effect generation. Users can create original audio by entering a text prompt and a duration, generating audio in high-quality, 44.1 kHz stereo. It uses a latent diffusion for audio model, trained on data from AudioSparx, a leading music library.

We are the world’s leading open source generative AI company

Our goal is to maximize the accessibility of modern AI to inspire global creativity and innovation.
generated image of a computer with a single blooming rose growing out

Since launching our AI initiative in 2021, we have amassed a community of more than 200,000 creators, developers, and researchers, as well as several research hubs spread across the world.

We strongly believe that our open source ethos provides the definitive path for the creation and access of cutting-edge research. Stability AI-backed research communities are currently developing breakthrough AI models applied to imaging, language, code, audio, video, 3D content, design, biotech, and other scientific research.

Our partnership with Amazon Web Services provides us with the world’s fifth-largest supercomputer – the Ezra-1 UltraCluster – supplying the necessary power to generate these advancements.

In August 2022, we co-launched the first release of Stable Diffusion, a pioneering text-to-image model for which we provided the use of Ezra-1. Stable Diffusion 2.0 was released in November 2022 and has been entirely funded and developed by Stability AI.

Creating applications on Stable Diffusion’s open-source platform has proved wildly successful. Shortly after the release of Stable Diffusion 2.0, a proliferation of mobile apps powered by the model were among the most downloaded online. The release of SDXL in April created further buzz, with its giant leap in aesthetics and prompt recognition.

Through DreamStudio, Stability AI’s premium imaging tool, and leading third-party apps like Lensa, Wonder, and NightCafe, the Stable Diffusion suite of image-generation models has amassed over 40 million users and counting.

April 2023 also saw the release of StableLM, the first of our suite of language models, as well as StableVicuna, the first large-scale open RLHF LLM Chatbot.