Stable Video Diffusion 1.1
Stable Video Diffusion 1.1 refines the earlier 25-frame SVD XT model. It was fine-tuned with fixed frame-rate and motion conditioning to make its default output more consistent.
Model design and access
The conditioning values remain adjustable, but the card warns that behavior outside the fine-tuning settings may differ from SVD 1.0. It retains the earlier model's lack of text control and limitations with motion, faces and readable text.Stable Video Diffusion 1.1 official model card
The Stable Video Diffusion API is no longer supported. The official release notes direct users to self-hosted deployment.Stability AI API release notes
Practical use
Practical guidance. Start with the documented conditioning when evaluating 1.1. Changing frame rate or motion strength is an experiment, not a guarantee of a longer or more accurate action. For a repeatable local workflow, save the input image, checkpoint and all motion settings together.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | SVD 1.1SVD XT 1.1 |
| Output | 25 frames at 1024 × 576.Stable Video Diffusion 1.1 official model card |
| Fine-tuning conditions | 6 FPS and motion bucket ID 127.Stable Video Diffusion 1.1 official model card |
| Current licensing | Included in the Community and Enterprise Core Models list.Stability AI Core Models: May 2026 list |
Related models
- Stable Video 3D
Stability AI · Stable Video
Stable Video 3D adapts Stable Video Diffusion to generate orbital views of an object from one image.
Launch date not confirmedDownloadable - Stable Video Diffusion
Stability AI · Stable Video
Stable Video Diffusion turns a still image into a short video.
Launch date not confirmedDownloadable