Preprint
Jul 2026
ProxyUp: Training-Free Proxy-Conditioned Video Generation for Controllable Dynamics
Experiments show that ProxyUp outperforms strong video editing and motion transfer baselines in dynamic fidelity and text alignment and progressively relaxes the composed latent toward the model's learned distribution before ODE sampling.
Zanwei Zhou, Jiazhong Cen, Jiemin Fang et al.
· 0 citations