Text-to-Video Generation on Human evaluation
87Visual QualityTF-T2V
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| TF-T2V2023.12 | 87 | 92.5 | 86.5 | — | |
| ModelScopeT2V2023.12 | 74 | 81.3 | 83.5 | — | |
| SGMD2026.05 | 14 | 71 | 4 | 65 | |
| DMD22026.05 | 12 | 24 | 6 | 13 | |
| HiGen2023.12 | 0.844 | 0.74 | 0.812 | — | |
| VideoCrafter2023.12 | 0.812 | 0.552 | 0.768 | — | |
| Text2Video-Zero2023.12 | 0.636 | 0.26 | 0.538 | — | |
| ModelScopeT2V2023.12 | 0.324 | 0.432 | 0.548 | — | |
| BaselineNumber of parameters=1.3B2025.10 | — | — | — | 15 | |
| Epipolar-DPONumber of parameters=1.3B2025.10 | — | — | — | 52.8 |