ByteDance Seedance 2.0

Seedance 2.0 is a text-to-video and image-to-video model developed by ByteDance's Seed AI research division. It generates short, high-resolution video clips from text prompts or still images, with a focus on realistic motion, temporal coherence, and complex prompt adherence. The model supports multiple input modalities including text, images, audio, and video, and offers advanced features like Director Mode for precise control over camera trajectories and lighting.