Stable Video Diffusion Now Available on Stability AI Developer Platform API — Stability AI

콘텐츠

We are pleased to announce the addition of Stable Video Diffusion, our foundational image-to-video model, to Stability AI’s Developer Platform API. This new addition provides programmatic access to the state-of-the-art video model designed for various sectors, including advertising, marketing, TV, film, and gaming. Our aim with this release is to provide developers with an efficient way to seamlessly integrate advanced video generation into their products.

With a focus on both performance and safety, the Stable Video Diffusion offers frame interpolation for 24fps video output and includes features such as safety measures and watermarking. Competitive in performance, the model can generate 2 seconds of video, comprising of 25 generated frames and 24 frames of FILM interpolation, within an average time of 41 seconds.

Developers can leverage its full capabilities through features like motion strength control and support for multiple layouts and resolutions, including 1024x576, 768x768, and 576x1024. The model is also compatible with image formats such as jpg and png. With seed-based control, developers can choose between repeatable or random generation. The final video output is delivered in MP4 format, facilitating easy integration into various applications and platforms.

Additionally, for your multi-modal needs, the Stability AI Developer platform offers a range of image generation models, including our flagship text-to-image model, Stable Diffusion XL.

Visit the Stability AI Developer Platform today to learn about pricing and get started.

We want customers to be able to access our models wherever and however they prefer, depending on their cost, performance, flexibility, and privacy needs. If you’d like to host our models locally, you can do so through the Stability AI membership.

Furthermore, you can sign up for our waitlist here to be one of the first to access an upcoming Stable Video web interface.

Get the latest on our products: subscribe to our newsletter, follow us on Twitter, Instagram, and LinkedIn. Join our Discord Community to connect with fellow builders and creators.

요약하다
Stability AI has added Stable Video Diffusion, an image-to-video model, to its Developer Platform API. The model is designed for sectors such as advertising, marketing, TV, film, and gaming. It offers frame interpolation for 24fps video output, safety measures, and watermarking. The model can generate 2 seconds of video in an average time of 41 seconds, with features like motion strength control and support for multiple layouts and resolutions. The final video output is in MP4 format. The Developer Platform also offers other image generation models, and customers can access the models through the Stability AI membership. A Stable Video web interface is upcoming, and interested individuals can sign up for the waitlist. For more information, pricing, and access, visit the Stability AI Developer Platform.