Stable Video Diffusion
Generates stable diffusion model videos from images.
About Stable Video Diffusion
Introducing Stable Video Diffusion, an innovative open-source generative AI model created by Stability AI. This cutting-edge model serves as the foundation for generating videos based on the renowned image model, Stable Diffusion. Currently in the research preview stage, Stable Video Diffusion's code is accessible on Stability AI's GitHub repository, with the necessary weights for local model operation conveniently located on their Hugging Face page. Adaptable to a wide array of video applications, this model can be easily fine-tuned for multi-view synthesis from a single image utilizing multi-view datasets. Offering exceptional performance when compared to closed models, external evaluations and user preference studies have validated Stable Video Diffusion's capabilities. It's essential to highlight that, for the time being, Stable Video Diffusion is designed exclusively for research purposes and is not intended for real-world or commercial use. Constructive feedback on safety and quality is highly valued to enhance the model prior to its official release. Part of Stability AI's diverse range of open-source models, Stable Video Diffusion joins modalities such as image, language, audio, 3D, and code. The company is dedicated to enhancing human intelligence and consistently updates its models with the latest advancements. To stay informed on Stability AI's advancements, users can subscribe to the newsletter and explore commercial applications by reaching out to the company. Additionally, updates can be followed on social media platforms like Twitter and Instagram.