Text-to-Video Generation on MSR-VTT (test)
0.3123CLIP SimilarityVideoPoet
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| VideoPoetzero-shot=true, variant=Task adapt2023.12 | 0.3123 | — | — | — | |
| Show-1zero-shot=true2023.12 | 0.3072 | — | 538 | — | |
| Make-A-VideoZero-Shot=Yes, Samples/Input=12022.09 | 0.3049 | 13.17 | — | — | |
| Make-A-VideoPre-training=20M, Zero-shot=true2022.11 | 0.3049 | 13.2 | — | — | |
| Make-A-VideoZero-Shot=true2023.05 | 0.3049 | — | — | — | |
| Make-A-VideoZero-shot=true2023.06 | 0.3049 | — | — | — | |
| Make-A-VideoTraining Data=WebVid-10M + HD-VILA-10M, Resolution=256x256, Zero-shot=Yes, Params(B)=9.722023.08 | 0.3049 | — | — | — | |
| Make-A-VideoZero-shot=true, Resolution=256x2562023.08 | 0.3049 | 13.17 | — | — | |
| Make-A-VideoZero-shot=Yes, Parameters=9.7B2023.12 | 0.3049 | 13.17 | — | — | |
| Make-A-VideoZero-shot=true2024.02 | 0.3049 | — | — | 13.17 | |
| Make-A-Videozero-shot=true2023.12 | 0.3049 | — | — | — | |
| VideoPoetzero-shot=true, variant=Pretrain2023.12 | 0.3049 | — | 213 | — | |
| Make-A-VideoData size=20M, Unified=false, Zero-shot=true2024.12 | 0.3049 | — | — | — | |
| VideoPoetData size=270M, Unified=false, Zero-shot=true2024.12 | 0.3049 | — | 213 | — | |
| Video-LavITData size=10M, Unified=true, Zero-shot=true2024.12 | 0.3012 | — | 188.36 | — | |
| VideoFactoryTraining Data=WebVid-10M + HD-VG-130M, Resolution=256x256, Zero-shot=Yes, Params(B)=2.042023.08 | 0.3005 | — | — | — | |
| VideoFactoryZero-shot=true2024.02 | 0.3005 | — | — | — | |
| VideoFactoryzero-shot=true2023.12 | 0.3005 | — | — | — | |
| TF-T2VZero-shot=Yes, Parameters=1.8B, Training Data=WebVid10M+Internal10M2023.12 | 0.2991 | 8.19 | 441 | — | |
| TF-T2VZero-shot=Yes, Parameters=1.8B, Training Data=WebVid10M2023.12 | 0.2953 | 9.67 | 484 | — | |
| InternVidzero-shot=true2023.12 | 0.2951 | — | — | — | |
| InternVidData size=28M, Unified=false, Zero-shot=true2024.12 | 0.2951 | — | — | — | |
| SimDATraining Data=WebVid-10M, Resolution=256x256, Zero-shot=Yes, Params(B)=1.082023.08 | 0.2945 | — | 456 | — | |
| Divot-LLMData size=4.8M, Unified=true, Zero-shot=true2024.12 | 0.2938 | — | 301.4 | — | |
| VILA-UData size=1M, Unified=true, Zero-shot=true2024.12 | 0.2937 | — | 499.06 | — | |
| VideoComposerZero-shot=true2023.06 | 0.2932 | — | 580 | — | |
| VideoComposerTraining Data=WebVid-10M, Resolution=256x256, Zero-shot=Yes, Params(B)=1.852023.08 | 0.2932 | — | 580 | — | |
| VideoComposerZero-shot=Yes, Parameters=1.9B2023.12 | 0.2932 | 10.77 | 580 | — | |
| VideoComposerData size=10M, Unified=false, Zero-shot=true2024.12 | 0.2932 | — | 580 | — | |
| ModelScopeT2VZero-shot=true, Resolution=256x2562023.08 | 0.293 | 11.09 | 550 | — | |
| ModelScopeT2VZero-shot=Yes, Parameters=1.7B2023.12 | 0.293 | 11.09 | 550 | — | |
| ModelScopeT2Vzero-shot=true2023.12 | 0.293 | — | 550 | — | |
| Video LDMZero-Shot=true2023.05 | 0.2929 | — | — | — | |
| Video LDMZero-shot=true2023.06 | 0.2929 | — | — | — | |
| Video-LDMTraining Data=WebVid-10M, Resolution=256x256, Zero-shot=Yes, Params(B)=4.202023.08 | 0.2929 | — | — | — | |
| Video LDMZero-shot=true, Resolution=256x2562023.08 | 0.2929 | — | — | — | |
| VideoLDMZero-shot=Yes, Parameters=4.2B2023.12 | 0.2929 | — | — | — | |
| Video LDMZero-shot=true2024.02 | 0.2929 | — | — | — | |
| Video LDMzero-shot=true2023.12 | 0.2929 | — | — | — | |
| Video LDMData size=10M, Unified=false, Zero-shot=true2024.12 | 0.2929 | — | — | — | |
| LoongData size=16M, Unified=false, Zero-shot=true2024.12 | 0.2903 | — | 274 | — | |
| CoDiZero-Shot=true2023.05 | 0.289 | — | — | — | |
| Text-to-video pre-training (First stage)Zero-shot=true2023.06 | 0.2876 | — | 803 | — | |
| VideoFusionTraining Data=WebVid-10M, Resolution=256x256, Zero-shot=Yes, Params(B)=1.832023.08 | 0.2795 | — | 581 | — | |
| Snap VideoResolution=288 x 288 px, Zero-shot=true2024.02 | 0.2793 | — | 110.4 | 8.48 | |
| Snap VideoResolution=512 x 288 px, Zero-shot=true2024.02 | 0.2793 | — | 104 | 9.35 | |
| Snap VideoUnified=false, Zero-shot=true2024.12 | 0.2793 | — | 110.4 | — | |
| Latent-ShiftTraining Data=WebVid-10M, Resolution=256x256, Zero-shot=Yes, Params(B)=1.532023.08 | 0.2773 | — | — | — | |
| Latent-ShiftZero-shot=Yes, Parameters=1.5B2023.12 | 0.2773 | 15.23 | — | — | |
| Latent-ShiftZero-shot=true2024.02 | 0.2773 | — | — | 15.23 | |
| ED-T2VTraining Data=WebVid-10M, Resolution=256x256, Zero-shot=Yes, Params(B)=1.302023.08 | 0.2763 | — | — | — | |
| MMVGPre-training=2.5M, Zero-shot=true2022.11 | 0.2644 | 23.4 | — | — | |
| MMVGTraining Data=WebVid-2.5M, Resolution=256x256, Zero-shot=Yes2023.08 | 0.2644 | — | — | — | |
| CogVideo (English)Zero-Shot=Yes, Samples/Input=1, Input Language=English2022.09 | 0.2631 | 23.59 | — | — | |
| CogVideoPre-training=5.4M, Zero-shot=true2022.11 | 0.2631 | 23.6 | — | — | |
| CogVideoZero-Shot=true2023.05 | 0.2631 | — | — | — | |
| CogVideo (English)Zero-shot=true2023.06 | 0.2631 | — | 1,294 | — | |
| CogVideoTraining Data=WebVid-5.4M, Resolution=256x256, Zero-shot=Yes, Params(B)=15.52023.08 | 0.2631 | — | 1,294 | — | |
| CogVideo (English)Zero-shot=true, Resolution=256x2562023.08 | 0.2631 | 23.59 | 1,294 | — | |
| CogVideo (English)Zero-shot=Yes, Parameters=15.5B2023.12 | 0.2631 | 23.59 | 1,294 | — | |
| CogVideoLanguage=English, Zero-shot=true2024.02 | 0.2631 | — | — | 23.59 | |
| CogVideo (EN)zero-shot=true2023.12 | 0.2631 | — | 1,294 | — | |
| Cog VideoData size=5.4M, Unified=false, Zero-shot=true2024.12 | 0.2631 | — | 1,294 | — | |
| CogVideo (Chinese)Zero-Shot=Yes, Samples/Input=1, Input Language=Chinese2022.09 | 0.2614 | 24.78 | — | — | |
| CogVideo (Chinese)Zero-shot=true2023.06 | 0.2614 | — | — | — | |
| CogVideo (Chinese)Zero-shot=true, Resolution=256x2562023.08 | 0.2614 | 24.78 | — | — | |
| CogVideo (Chinese)Zero-shot=Yes, Parameters=15.5B2023.12 | 0.2614 | 24.78 | — | — | |
| CogVideoLanguage=Chinese, Zero-shot=true2024.02 | 0.2614 | — | — | 24.78 | |
| NÜWAZero-Shot=No2022.09 | 0.2439 | 47.68 | — | — | |
| NUWAPre-training=3.9M, Zero-shot=false2022.11 | 0.2439 | 47.7 | — | — | |
| NÜWAZero-Shot=false2023.05 | 0.2439 | — | — | — | |
| NüwaZero-shot=false2023.06 | 0.2439 | — | — | — | |
| NÜWATraining Data=MSR-VTT, Resolution=128x128, Zero-shot=No, Params(B)=0.872023.08 | 0.2439 | — | — | — | |
| NÜWAZero-shot=true, Resolution=256x2562023.08 | 0.2439 | 47.68 | — | — | |
| NüwaZero-shot=No, Parameters=-2023.12 | 0.2439 | 47.68 | — | — | |
| NUWALanguage=Chinese, Zero-shot=true2024.02 | 0.2439 | — | — | 47.68 | |
| GODIVAZero-Shot=No, Samples/Input=302022.09 | 0.2402 | — | — | — | |
| GODIVAPre-training=136M, Zero-shot=false2022.11 | 0.2402 | — | — | — | |
| GODIVAZero-Shot=false2023.05 | 0.2402 | — | — | — | |
| GODIVAZero-shot=false2023.06 | 0.2402 | — | — | — | |
| GODIVATraining Data=MSR-VTT, Resolution=128x128, Zero-shot=No2023.08 | 0.2402 | — | — | — | |
| MMVGZero-shot=false2022.11 | 0.2385 | 60.6 | — | — | |
| LVDMTraining Data=WebVid-2M, Resolution=256x256, Zero-shot=Yes, Params(B)=1.162023.08 | 0.2381 | — | 742 | — | |
| LVDMZero-shot=true2024.02 | 0.2381 | — | — | — | |
| TATSZero-shot=false2022.11 | 0.2326 | 63.2 | — | — | |
| Magic VideoZero-shot=true2023.06 | — | — | 1,290 | — | |
| Magic VideoTraining Data=WebVid-10M, Resolution=256x256, Zero-shot=Yes2023.08 | — | — | 998 | — | |
| Magic VideoZero-shot=true, Resolution=256x2562023.08 | — | — | 1,290 | — | |
| Magic VideoZero-shot=true2024.02 | — | — | 998 | — | |
| MagicVideoZero-shot=Yes, Parameters=-2023.12 | — | — | 1,290 | — | |
| MagicVideozero-shot=true2023.12 | — | — | 998 | — | |
| PYoCoZero-shot=Yes, Parameters=-2023.12 | — | 9.73 | — | — | |
| PYoCoZero-shot=true2024.02 | — | — | — | 9.73 |