Search papers, labs, and topics across Lattice.
Bytedance Seed
2
0
6
Humanoid states, not low-level actions, are the key to unlocking text-driven control, enabling a diffusion model to generate more natural and semantically aligned behaviors.
Seedance 2.0 leapfrogs existing models by unifying multi-modal inputs (text, image, audio, video) into a single architecture for generating high-quality, longer-duration audio-video content.
