Seedance 2.5

Video Models

generateanimatetext to videoimage to videostart frameend frame

Overview

Latest generation video model with native audio, 4-30 second duration, and 480p/720p output. Supports text-to-video, image-to-video, and first+last frame modes. To drive generation with reference images, videos, or audio instead, use Seedance 2.5 Omni Reference - frame images and reference material cannot be combined in one generation.

Accepts up to 2 image inputs: first frame and end frame.

First frame
End frame