Text-to-Video Generation on UCF-101
81FVDMake-A-Video
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Make-A-VideoPre-training=20M2022.11 | 81 | 82.6 | |
| SVDData size=152M, Public data=false, Zero-shot=true2024.02 | 242.02 | — | |
| Video-LaVITData size=10M, Public data=true, Zero-shot=true2024.02 | 280.57 | 44.26 | |
| HPDM-T2VResolution=72 x 128, Zero-shot=true2024.06 | 299.3 | 20.53 | |
| Dysen-VDMZero-shot=true2023.08 | 325.42 | 35.57 | |
| MMVGPre-training=None2022.11 | 328 | 73.7 | |
| TATSPre-training=None2022.11 | 341 | 71.6 | |
| VideoPoetData size=270M, Public data=false, Zero-shot=true2024.02 | 355 | 38.44 | |
| VideoPoetzero-shot=true, variant=Pretrain2023.12 | 355 | 38.44 | |
| PYoCoData size=22.5M, Public data=false, Zero-shot=true2024.02 | 355.19 | 47.76 | |
| PYoCoResolution=256 x 256, Zero-shot=true2024.06 | 355.2 | 47.46 | |
| Make-A-Videozero-shot=true2023.12 | 367 | 33 | |
| Make-A-VideoResolution=256 x 256, Zero-shot=true2024.06 | 367.2 | 33 | |
| Make-A-VideoZero-Shot=true2023.04 | 367.23 | 33 | |
| Make-A-VideoZero-Shot=true2023.04 | 367.23 | 33 | |
| Make VideoZero-shot=true2023.08 | 367.23 | 33 | |
| Make-A-VideoData size=20M, Public data=true, Zero-shot=true2024.02 | 367.23 | 33 | |
| Make-A-Video2023.09 | 367.23 | 33 | |
| Show-1Fine-tuning=square videos2023.09 | 369.33 | 36.02 | |
| HPDM-T2VResolution=144 x 256, Zero-shot=true2024.06 | 383.3 | 21.15 | |
| Show-1Input transformation=resized2023.09 | 383.46 | 35.67 | |
| Show-1zero-shot=true2023.12 | 394 | 35.42 | |
| VideoFactoryZero-shot=true2023.08 | 410 | — | |
| VideoFactoryzero-shot=true2023.12 | 410 | — | |
| VideoFactoryResolution=256 x 256, Zero-shot=true2024.06 | 410 | — | |
| VideoFactory2023.09 | 410 | — | |
| HPDM-T2V-1KResolution=576 x 1024, Zero-shot=true2024.06 | 447.5 | 24.51 | |
| HPDM-T2VResolution=288 x 512, Zero-shot=true2024.06 | 481.9 | 23.77 | |
| ShowMakerZero-shot=true, Prompt type=Class label2024.01 | 525.01 | — | |
| Video LDMResolution=N/A, Zero-shot=true2024.06 | 550.6 | 33.45 | |
| Video LDMZero-Shot=true, Base Model=SD 2.12023.04 | 550.61 | 33.45 | |
| Video LDMZero-Shot=true2023.04 | 550.61 | 33.45 | |
| Video LDMZero-shot=true, Prompt type=Class label2024.01 | 550.61 | — | |
| AlignLatentZero-shot=true2023.08 | 550.61 | 33.45 | |
| Video LDMData size=10M, Public data=true, Zero-shot=true2024.02 | 550.61 | 33.45 | |
| Video LDM2023.09 | 550.61 | 33.45 | |
| Video LDMzero-shot=true2023.12 | 551 | 33.45 | |
| InternVidZero-shot=true2023.08 | 616.51 | 21.04 | |
| InternVidData size=28M, Public data=true, Zero-shot=true2024.02 | 616.51 | 21.04 | |
| InternVidzero-shot=true2023.12 | 617 | 21.04 | |
| CogVideoPre-training=5.4M2022.11 | 626 | 50.5 | |
| LVDMResolution=256 x 256, Zero-shot=true2024.06 | 641.8 | — | |
| MagicVideozero-shot=true2023.12 | 655 | — | |
| Magic VideoResolution=256 x 256, Zero-shot=true2024.06 | 655 | — | |
| Magic Video2023.09 | 655 | — | |
| Video LDMZero-Shot=true, Base Model=SD 1.42023.04 | 656.49 | 29.49 | |
| Magic VideoZero-Shot=true2023.04 | 699 | — | |
| Magic VideoZero-Shot=true2023.04 | 699 | — | |
| MagicVideoZero-shot=true, Prompt type=Class label2024.01 | 699 | — | |
| Magic VideoZero-shot=true2023.08 | 699 | — | |
| CogVideo (English)Zero-Shot=true2023.04 | 701.59 | 25.27 | |
| CogVideo (English)Zero-Shot=true2023.04 | 701.59 | 25.27 | |
| CogVideo (English)Zero-shot=true, Prompt type=Class label, Language=English2024.01 | 701.59 | — | |
| CogVideoZero-shot=true2023.08 | 701.59 | 25.27 | |
| CogVideoData size=5.4M, Public data=true, Zero-shot=true2024.02 | 701.59 | 25.27 | |
| CogVideoLanguage=English2023.09 | 701.59 | 25.27 | |
| CogVideoResolution=128 x 128, Zero-shot=true2024.06 | 701.6 | 25.27 | |
| CogVideo (EN)zero-shot=true2023.12 | 702 | 25.27 | |
| CogVideo (Chinese)Zero-Shot=true2023.04 | 751.34 | 23.55 | |
| CogVideo (Chinese)Zero-Shot=true2023.04 | 751.34 | 23.55 | |
| CogVideo (Chinese)Zero-shot=true, Prompt type=Class label, Language=Chinese2024.01 | 751.34 | — |