Private AI
Kuaishou's unified multi-modal video model with MVL technology. Supports text-only input for text-to-video, image input for image-to-video, video input for editing, or combined input for reference-based generation.
Added Dec 1, 2025
Approx. Price
$0.560 per video
Model Type
both
Generation controls available for this model.
Output Format
Default Duration
5
2 duration options
Aspect Ratio
Default
16:9
Options (3)
16:9 (Landscape), 9:16 (Portrait), 1:1 (Square)
Video aspect ratio
Duration
Default
5
Options (2)
5 seconds, 10 seconds
Video duration in seconds
Keep Original Sound
Default
true
Options (2)
Yes, No
Preserve original audio when using video input
Mode
Default
auto
Options (3)
Auto-detect, Edit Video, Reference to Video
How to process video input: Edit modifies the video, Reference uses it as style guidance for new generation
No benchmark data is available yet for this model.
Loading examples…