ByteDance's top-ranked AI video model is now live in Canvas.

Seedance 2.0 brings multimodal reference generation, with ability to combine up to 9 images, 3 video clips, and 3 audio files in a single generation.

Key capabilities: use video to add movement to characters and scenes, realistic movement physics, character consistency across shots, native audio generation, and director-level control.

Learn how to use Seedance 2.0 → Seedance 2.0 Workflow and Prompt Guide