Stable Diffusion
Open models in every modality, for everyone, everywhere.
4.9•15 reviews•369 followers
Open models in every modality, for everyone, everywhere.
4.9•15 reviews•369 followers
Stable Fast 3D transforms a single input image into a detailed 3D asset, setting a new standard for speed and quality in the field of 3D reconstruction.
This is the 5th launch from Stable Diffusion. View more
Stable Audio 3.0
Launching today
Stable Audio 3.0 is a model family trained on fully licensed data, designed to be the foundation for what the audio community builds next. Three of the models are open weights, free to download and build on.
Free Options
Launch Team
Flowtica Scribe
Hi everyone!
Stable Audio is now in its 3rd generation, and the open / commercial strategy looks much more mature.
Small, Small SFX, and Medium are available with open weights for experimentation and builders. The larger flagship model is available through the Stability AI API or enterprise self-hosting.
Medium and Large can generate full compositions up to 6 minutes, which is honestly pretty astonishing.
That is a pretty practical split. Smaller models can grow the developer and creative ecosystem, while the flagship model stays closer to professional production, licensing, and support.
For music and sound, this matters. The category needs both experimentation and a safer commercial path.