Stable Video Diffusion
Stability AI’s First Open Video Model.
Stable Video Diffusion is designed to serve a wide range of video applications in fields such as media, entertainment, education, marketing. It empowers individuals to transform text and image inputs into vivid scenes and elevates concepts into live action, cinematic creations.
Read the Research Paper
Stable Video Diffusion Specifications
Stable Video Diffusion is released in the form of two image-to-video models, capable of generating 14 and 25 frames at customizable frame rates between 3 and 30 frames per second.
At the time of release in their foundational form, we have found these models surpass the leading closed models in user preference studies.
Video duration
2-5 seconds
Frame rate
up to 30 FPS (frames per second)
Processing time
2 minutes or less
Stable Video Diffusion License
Please read and review the License in full before using Stable Video Diffusion.
Stable Video Diffusion is now available for use under a non-commercial community license (the “License”) which can be found here.
Stability AI is making Stable Video Diffusion freely available to you, including model code and weights, for research and other non-commercial purposes. Your use of Stable Video Diffusion is subject to the terms of the License, which includes the use and content restrictions found in Stability’s Acceptable Use Policy.
The license reflects Stability’s dual commitments to making its research widely available while working to ensure that its AI models are used to benefit humanity.
Build with a Stability AI Membership
The Stability AI Membership offers flexibility for your generative AI needs by combining our range of state-of-the-art open models with self-hosting benefits.