Stability AI has launched its new generative AI video model, Stable Video Diffusion, available in a research preview.
The model's code and weights are provided on GitHub and Hugging Face, facilitating local implementation and research.
Stable Video Diffusion supports a Text-To-Video interface and is targeted toward numerous sectors such as Advertising and Education.
Performance evaluations indicate user preference for Stability AI’s models over other leading closed models.
Currently exclusive for research, the company welcomes feedback on safety and quality for future improvements and commercial release.

Stability AI is a startup focused on creating state-of-the-art artificial intelligence models and promoting open-source collaboration. It provides a platform for developers to contribute to and build applications using their foundational model, Stable Diffusion XL. They are pushing the boundaries in audio diffusion to generate high-quality music and sound effects, and they maintain a commitment to open access language models, competing with industry leaders. Stability AI has also developed the first open generative AI video model based on their image model. They emphasize community involvement and offer updates through a newsletter subscription.

Stability AI

Stability AI offers the Stable Diffusion model for images, audio, and language.

Stable Video Diffusion Unveiled by Stability AI

Recent Product News