Back to All Resources

Stable Video Diffusion

Stable Video Diffusion, developed by Stability AI, is a state-of-the-art model for text-to-video and image-to-video generation. The model features two variants capable of producing 14 and 25 frames, with customizable frame rates ranging between 3 and 30 frames per second. It incorporates robust multi-view 3D priors, enhancing the consistency and realism of generated video sequences. Stable Video Diffusion can also fine-tune multi-view diffusion models, enabling the creation of dynamic, high-fidelity videos suitable for creative and professional applications.