Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance
Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity, scene layout, motion, and fine details across time. Existing training-free methods mainly strengthen cross-frame attention or analyze loca...
Lu-Yao Tang, Bin Luo, Dong Yi et al.
· 1 citation