Video Generation on MSRVTT (val)
414FVDMCM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=4, zero-shot=true2024.06 | 414 | 28.86 | |
| MCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=2, zero-shot=true2024.06 | 434 | 29.02 | |
| DPM++Teacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=4, zero-shot=true2024.06 | 467 | 28.51 | |
| MCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=8, zero-shot=true2024.06 | 482 | 28.28 | |
| MCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=1, zero-shot=true2024.06 | 501 | 28.37 | |
| DPM++Teacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=8, zero-shot=true2024.06 | 552 | 29.7 | |
| MCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=8, zero-shot=true2024.06 | 675 | 29.13 | |
| LCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=4, Implementation=our impl., zero-shot=true2024.06 | 713 | 28.45 | |
| LCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=8, Implementation=our impl., zero-shot=true2024.06 | 717 | 29.01 | |
| AnimateLCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=8, zero-shot=true2024.06 | 740 | 27.67 | |
| DPM++Teacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=8, zero-shot=true2024.06 | 794 | 29.1 | |
| MCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=4, zero-shot=true2024.06 | 801 | 29.64 | |
| LCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=2, Implementation=our impl., zero-shot=true2024.06 | 820 | 28.01 | |
| AnimateLCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=4, zero-shot=true2024.06 | 824 | 29.58 | |
| LCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=8, Implementation=our impl., zero-shot=true2024.06 | 830 | 28.65 | |
| DDIMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=8, zero-shot=true2024.06 | 841 | 26.76 | |
| DPM++Teacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=4, zero-shot=true2024.06 | 876 | 27.62 | |
| AnimateDiff-LightningTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=4, zero-shot=true2024.06 | 892 | 29.12 | |
| AnimateDiff-LightningTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=8, zero-shot=true2024.06 | 932 | 28.77 | |
| DDIMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=8, zero-shot=true2024.06 | 933 | 27.36 | |
| LCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=4, Implementation=our impl., zero-shot=true2024.06 | 956 | 28.37 | |
| MCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=2, zero-shot=true2024.06 | 1,036 | 29.4 | |
| LCMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=1, Implementation=our impl., zero-shot=true2024.06 | 1,094 | 26.78 | |
| LCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=2, Implementation=our impl., zero-shot=true2024.06 | 1,180 | 27.33 | |
| MCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=1, zero-shot=true2024.06 | 1,197 | 28.95 | |
| AnimateDiff-LightningTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=2, zero-shot=true2024.06 | 1,259 | 28.77 | |
| AnimateDiff-LightningTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=1, zero-shot=true2024.06 | 1,260 | 27.38 | |
| LCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=1, Implementation=our impl., zero-shot=true2024.06 | 1,276 | 25.75 | |
| AnimateLCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=2, zero-shot=true2024.06 | 1,278 | 28.52 | |
| DPM++Teacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=2, zero-shot=true2024.06 | 1,336 | 24.85 | |
| DDIMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=4, zero-shot=true2024.06 | 1,445 | 22.57 | |
| DPM++Teacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=2, zero-shot=true2024.06 | 1,447 | 24.5 | |
| AnimateLCMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=1, zero-shot=true2024.06 | 1,578 | 27.56 | |
| DPM++Teacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=1, zero-shot=true2024.06 | 2,004 | 22.93 | |
| DPM++Teacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=1, zero-shot=true2024.06 | 2,039 | 23.48 | |
| DDIMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=2, zero-shot=true2024.06 | 2,305 | 20.33 | |
| DDIMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=4, zero-shot=true2024.06 | 2,774 | 22.87 | |
| DDIMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=2, zero-shot=true2024.06 | 4,350 | 20.94 | |
| DDIMTeacher=AnimateDiff, Resolution=512x512x16, Sampling Steps=1, zero-shot=true2024.06 | 4,782 | 20.9 | |
| DDIMTeacher=ModelScopeT2V, Resolution=256x256x16, Sampling Steps=1, zero-shot=true2024.06 | 6,459 | 21.49 |