Stable Video Diffusion is an open-source generative AI model developed by Stability AI. It is the company’s first foundation model for generating videos based on the image model Stable Diffusion.
The model is currently in a research preview stage.The code for Stable Video Diffusion is available on Stability AI’s GitHub repository, and the weights required to run the model locally can be found on their Hugging Face page.
The model is adaptable to various video applications and can be easily fine-tuned for multi-view synthesis from a single image using multi-view datasets.Stable Video Diffusion offers competitive performance compared to other closed models, as evidenced by external evaluation and user preference studies.It’s important to note that at this stage, Stable Video Diffusion is exclusively intended for research purposes and not for real-world or commercial applications.
Feedback on safety and quality is valuable for further refining the model before its eventual release.Stable Video Diffusion is part of Stability AI’s diverse range of open-source models, which includes modalities like image, language, audio, 3D, and code.
The company is committed to amplifying human intelligence and regularly updates its models with the latest advancements.To stay updated on Stability AI’s progress, users can sign up for the newsletter and explore commercial applications by contacting the company.
Social media platforms like Twitter and Instagram are also available for following Stability AI’s updates.
