one Reference-to-Video keeps characters, scenes, and voices aligned. It accepts 1 to 15 reference images and up to 3 audio clips, then generates a consistent 3 to 16 second video from 540p to 4K across five aspect ratios. It fits dialogue scenes, advertising characters, and multi-subject shots.
Up to 15 Reference ImagesUp to 3 Reference Audios3 to 16 Second Audio540p to 4KFive Aspect RatiosSubject ConsistencyWatermark Off
reference-to-video 756
Playground
Input
*API Key
Please select API Key
*prompt
*imageUrls
Upload Image
Supports JPG/PNG format, file size no more than 10MB
audioUrls
Upload Image
Supports JPG/PNG format, file size no more than 10MB