AI Trace
Creative GenerationVerified

Reviewed and published by trentmaziarz, May 11, 2026. Discovered and drafted by our automated research pipeline.

Stability AI offers Stable Video Diffusion, a model that takes a still image as input and generates a short video clip from it. The model is available to developers via the Stability AI Developer Platform API and has been used in sectors including advertising, gaming, and film.

Details

Stable Video Diffusion (SVD) is a latent diffusion model that generates 14 or 25 frames of video at customizable frame rates between 3 and 30 frames per second from a single conditioning image. The API version produces 2-second video clips in an average of 41 seconds and supports motion strength control and multiple resolutions. A companion model, Stable Video 4D 2.0 (SV4D 2.0), extends this to multi-view 4D asset generation from a single object-centric video, available for both commercial and non-commercial use.

Products affected

Stable Video DiffusionStable Video 4DStable Video 4D 2.0Stability AI Developer Platform APIStable Assistant

Sources & Evidence

Cite this record

Trace Foundation. (2026). Stability AI: Stability AI offers Stable Video Diffusion, a model that takes a still image as input and generates a short video clip from it. The model is available to developers via the Stability AI Developer Platform API and has been used in sectors including advertising, gaming, and film (data as of 2026-05-11) [Data set record]. AI Trace. https://www.aitrace.org/r/practice/bd37fb0f-bcf9-4e21-9f24-451da4005e1c. Accessed October 5, 2026.

Stable link
https://www.aitrace.org/r/practice/bd37fb0f-bcf9-4e21-9f24-451da4005e1c
Data as of
May 11, 2026
Last verified
May 11, 2026

How to cite AI Trace

Other practices by Stability AI

Have evidence about Stability AI's AI practices? Submit a report.

Report a Sighting →