However, the actual performance of the SVD 1.1 model remains to be seen. While Stability AI claims improvement, the Hugging Face page for the model notes it is for research purposes and warns that some of the original issues might still occur. Stability AI also released the Stable Video Diffusion API, which allows developers to integrate advanced video generation into their products. The company, founded in 2019, has been pushing the bar on generative AI with frequent model releases and raised significant funding, including a $101 million round in 2022.
Key takeaways:
- Stability AI has announced an upgrade for its image-to-video latent diffusion model, Stable Video Diffusion (SVD), called SVD 1.1. The updated model is optimized to generate short AI videos with better motion and more consistency.
- The new model is available for public use and can be downloaded via Hugging Face. It will also be provided as part of Stability’s subscription memberships, with different tiers for individual and enterprise users.
- SVD 1.1 generates four-second videos with 25 frames at a resolution of 1024×576 given a context frame of the same size. It is expected to deliver more consistent video outputs as compared to the original model.
- Stability AI has also released the Stable Video Diffusion API, which allows developers to integrate advanced video generation into their products. The API supports motion strength control and multiple layouts and resolutions.