Video Generation on MSR-VTT
245FVDMagDiff
Evaluation results
| Method | Links | |
|---|---|---|
| MagDiffInput Type=text&image-to-video, Training Videos=5.3M | 76K, Zero-shot=true2023.11 | 245 | |
| CAT-LVDM (BCNI)#Params=~0.6B, #Videos=~2M2025.05 | 358.3 | |
| CAT-LVDM (BCNI)#Params=~0.6B, #Videos=~2M2025.05 | 358.3 | |
| CAT-LVDM (SACN)#Params=~0.6B, #Videos=~2M2025.05 | 361 | |
| CAT-LVDM (SACN)#Params=~0.6B, #Videos=~2M2025.05 | 361 | |
| Video Crafter1Input Type=text&image-to-video, Training Videos=10.3M, Zero-shot=true2023.11 | 465 | |
| ModelScopeInput Type=text-to-video, Training Videos=10M, Zero-shot=true2023.11 | 550 | |
| VideoComposerInput Type=text&image-to-video, Training Videos=10.3M, Zero-shot=true2023.11 | 580 | |
| ModelScopeenhancement=PEEKABOO2023.12 | 609 | |
| MAGVIT#Params=~473M, #Videos=~20M2025.05 | 698 | |
| MAGVIT#Params=~473M, #Videos=~20M2025.05 | 698 | |
| ModelScope2023.12 | 868 | |
| MagicVideo2023.12 | 1,290 | |
| CogVideo (English)2023.12 | 1,294 | |
| CogVideo (Chinese)#Params=~9.4B, #Videos=~5.4M2025.05 | 1,294 | |
| CogVideo (Chinese)#Params=~9.4B, #Videos=~5.4M2025.05 | 1,294 |