MagicVideo: Efficient Video Generation With Latent Diffusion Models

Benchmark Model Rank Results
text-to-video-generation-on-msr-vttMagicVideo–FVD: 998FID: 36.5
text-to-video-generation-on-ucf-101MagicVideo (Zero-shot, 256x256)–FVD16: 699
video-generation-on-ucf-101MagicVideo (256x256, text-conditional)–FVD16: 699