Seedance 1.0 is a large-scale video generative model that supports multi-shot video generation from both text and image. It achieves breakthroughs in semantic understanding and prompt following, and can create videos with smooth motion, rich details, and cinematic aesthetics. It features a wide dynamic range, enabling smooth generation of large-scale movements. From subtle expressions to active scenes, it maintains a high level of stability and physical realism. Seedance can accurately interpret diverse stylistic prompts to support a wide range of creative needs, from photorealism and cyberpunk to illustration and felt texture.