Stable Video Diffusion
AI video generation model from Stability AI
About
Stable Video Diffusion is the video generation model family from Stability AI, distributed in the generative-models repository alongside related work like SV3D and SV4D. SVD produces short clips at 576 by 1024 resolution from an input image or context frame using a temporally-aware decoder. Weights are released under the CreativeML Open RAIL++-M license; the model is image-conditioned and is not intended as a text-to-image system.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Video Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- License
- Stability AI License
- Minimum VRAM
- 16 GB
- Added
- Jan 29, 2026
Related Tools
Text-to-video generation framework with cascaded latent diffusion.
Turn text-to-image models into animation generators
AI animation tool for creating dynamic video content
Latest Open-Sora release with improved video generation quality.
Open video generation model by Genmo focused on motion quality.
Updated CogVideo model by Zhipu AI with improved video quality.