Text-to-Video Generation on MSR-VTT
0.3204CLIPSIMDysen-VDM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Dysen-VDMZero-shot=true2023.08 | 0.3204 | 12.64 | — | |
| Make-A-VideoZero-Shot=true2023.04 | 0.3049 | — | — | |
| Make-A-VideoZero-Shot=true2023.04 | 0.3049 | — | — | |
| Make VideoZero-shot=true2023.08 | 0.3049 | 13.17 | — | |
| Make-A-VideoData size=20M, Public data=true, Zero-shot=true2024.02 | 0.3049 | 13.17 | — | |
| VideoPoetData size=270M, Public data=false, Zero-shot=true2024.02 | 0.3049 | — | 213 | |
| Video-LaVITData size=10M, Public data=true, Zero-shot=true2024.02 | 0.3012 | 11.27 | 188.36 | |
| VideoFactoryZero-shot=true2023.08 | 0.3005 | — | — | |
| InternVidZero-shot=true2023.08 | 0.2951 | — | — | |
| InternVidData size=28M, Public data=true, Zero-shot=true2024.02 | 0.2951 | — | — | |
| VideoComposerData size=10M, Public data=true, Zero-shot=true2024.02 | 0.2932 | — | 580 | |
| Video LDMBackbone=SD 2.1, Zero-Shot=true2023.04 | 0.2929 | — | — | |
| Video LDMZero-Shot=true2023.04 | 0.2929 | — | — | |
| AlignLatentZero-shot=true2023.08 | 0.2929 | — | — | |
| Video LDMData size=10M, Public data=true, Zero-shot=true2024.02 | 0.2929 | — | — | |
| Video LDMBackbone=SD 1.4, Zero-Shot=true2023.04 | 0.2848 | — | — | |
| Latent-ShiftZero-shot=true2023.08 | 0.2773 | 15.23 | — | |
| Latent-VDMZero-shot=true2023.08 | 0.2756 | 14.25 | — | |
| CogVideo (English)Zero-Shot=true2023.04 | 0.2631 | — | — | |
| CogVideo (English)Zero-Shot=true2023.04 | 0.2631 | — | — | |
| CogVideoZero-shot=true2023.08 | 0.2631 | 23.59 | — | |
| CogVideoData size=5.4M, Public data=true, Zero-shot=true2024.02 | 0.2631 | 23.59 | 1,294 | |
| CogVideo (Chinese)Zero-Shot=true2023.04 | 0.2614 | — | — | |
| CogVideo (Chinese)Zero-Shot=true2023.04 | 0.2614 | — | — | |
| NÜWAZero-Shot=false2023.04 | 0.2439 | — | — | |
| NÜWAZero-Shot=false2023.04 | 0.2439 | — | — | |
| GODIVAZero-Shot=false2023.04 | 0.2402 | — | — | |
| GODIVAZero-Shot=false2023.04 | 0.2402 | — | — | |
| CogVideoModel Type=T2V2024.03 | — | 23.59 | 1,294 | |
| Make-A-VideoModel Type=T2V2024.03 | — | 13.17 | — | |
| ModelScopeT2VModel Type=T2V2024.03 | — | 11.09 | 550 | |
| PYoCoData size=22.5M, Public data=false, Zero-shot=true2024.02 | — | 9.73 | — | |
| VideoComposerModel Type=T2V2024.03 | — | — | 580 |