Stable Video Diffusion
Stability AI's image-to-video latent diffusion model (SVD-XT: 25 frames at 576x1024), downloadable under the Stability AI Community License.
Visit Stable Video DiffusionFree (open source) · Free plan · checked Oct 26, 2026
Stable Video Diffusion at a glance
| Type | Open-source model |
|---|---|
| Developer | Stability AI |
| Starts at | Free (open source) |
| Billing | Open source (free) |
| Free plan | Free plan: Open weights on Hugging Face; commercial use per the Stability AI licence. |
| Watermark | Not stated |
| Max resolution | 576x1024 |
| Max length | Not stated |
| Commercial use | Not stated. "For commercial use, please refer to https://stability.ai/license." |
| API | Not stated |
What Stable Video Diffusion says it can do
- Image to video:
(SVD) Image-to-Video is a latent diffusion model trained to generate short video clips from an image conditioning.
source - Open weights:
The model is intended for both non-commercial and commercial usage.
source
Stable Video Diffusion alternatives
12 tools with the most overlap: CogVideoX, HunyuanVideo, LTX-2 / LTX-Video, MAGI-1, Open-Sora, SkyReels, Wan, Genmo and more. Compare all 12 Stable Video Diffusion alternatives →
Stable Video Diffusion compared
Where Stable Video Diffusion ranks
Positions in our lists, from public data only (same grey chip for every position).
- #8 in open-source AI video generators · ranked by public data
- #19 in free image-to-video AI generators · ranked by public data
- #28 in image-to-video AI generators · ranked by public data
- #40 in free AI video generators · ranked by public data
Sources
- https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt
- https://stability.ai/stable-video
Checked Oct 26, 2026 on Stable Video Diffusion's own site. Prices change; confirm on the vendor's site before you buy. Spotted an error? Send a correction.