VideoComposer: Compositional Video Synthesis with Motion Controllability

Benchmark Model Rank Results
text-to-video-generation-on-evalcrafter-textModelScope#5Visual Quality: 52.47Motion Quality: 53.09Temporal Consistency: 54.46
text-to-video-generation-on-msr-vttVideoComposer#6FVD: 580CLIPSIM: 0.2932