
ByteDance's multimodal video model for text, keyframes, image, video, and audio references with stable subjects and natural motion.

Generated in 38.6 seconds
Choose the same three routing tiers used across MLMux. The selected route is included as route_mode in every request.
Seedance 2.0 is available through MLMux with one request shape and three explicit provider routes.
Create advertising, social, and previsualization clips with clear subject movement and controlled camera direction.
Use images for identity and style, video for motion language, and audio to guide rhythm and synchronized sound.
Choose exact clip lengths from 4 to 30 seconds and select an output resolution for the intended delivery channel.