Model Library
Explore our image-to-video AI models to power your creative projects
wan2.5-i2v-preview version, supporting video generation with audio
Core Capabilities
Image to Video
Generate smooth video content based on first frame image and text prompts
Audio-Visual Sync
Support automatic dubbing or custom audio for perfect audio-visual synchronization
Smart Rewriting
Use AI model to intelligently rewrite input prompts for enhanced generation results
Multiple Resolutions
Support 480P, 720P, 1080P resolutions to meet different needs
Technical Specifications
- •Support automatic dubbing or custom audio upload
- •Resolution: 480P, 720P, 1080P
- •Video duration: 5 seconds, 10 seconds
- •Fixed specifications: 24fps, MP4 (H.264 encoding)