S

Stable Video Diffusion Img2vid Xt 1 1

Developed by weights
A latent diffusion model for generating short video clips from static images, supporting 25-frame video generation at 1024x576 resolution
Downloads 682
Release Time : 6/25/2024

Model Overview

This model is fine-tuned from the SVD image-to-video base model, specializing in generating coherent short video sequences from a single image, suitable for creative content generation and research purposes

Model Features

High-Resolution Video Generation
Supports 25-frame video generation at 1024x576 resolution
Static Image Driven
Only requires a single static image as input to generate coherent video clips
Research-Friendly
Provides complete codebase support for generative model and safe deployment research

Model Capabilities

Image-to-Video Conversion
Short Video Generation
Creative Content Generation

Use Cases

Creative Arts
Dynamic Art Creation
Transforming static artworks into dynamic presentations
Generates artistic animations within 4 seconds
Education & Research
Generative Model Research
Used for academic research on video generation algorithms
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase