Back to events
Open-source releaseLimited global significanceConfirmed confidence

Stability AI releases Stable Video Diffusion

Stability AI releases Stable Video Diffusion as a research preview and opens its code and model weights.

Event details

Stable Video Diffusion is an image-to-video foundation model based on Stable Diffusion. The first SVD and SVD-XT variants generate 14 and 25 frames respectively. The release is intended mainly for research and is not recommended for commercial or production use.

Why it matters

The release provides a locally runnable base model for open video-generation research, although its initial clip length, quality and usage scope are limited.

39/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.

Access notes

Code and weights are public, with research-only use stated at launch.