Stable Video Diffusion is an open-weight image-to-video diffusion model published by Stability AI on Hugging Face. Developers can run it locally with Diffusers and related Python libraries to generate short video clips from still images.
Stable Video Diffusion Img2vid is a Video generation project. It focuses on generating short animated videos from still images without building a video-generation model. It is built as an open-source project for AI developers and researchers. Stable Video Diffusion Img2vid is open source under the MIT license. Stable Video Diffusion Img2vid is available on the web, the command line, and API, and it can be self-hosted.
Behind Stable Video Diffusion Img2vid is Stability AI, and it first shipped in 2023. Development happens publicly on GitHub with 27.3k stars. Key capabilities include image-to-video generation, diffusion pipeline, and local inference.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do