Search papers, labs, and topics across Lattice.
2
0
5
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.
Ditch the training overhead and still get up to 4.79x faster diffusion sampling with Spectrum, a training-free feature forecasting method that actually maintains image quality.
