Text-to-Video on 220 text prompts
10.26OF ScoreBase model
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Base modelSampling Steps=40, Guidance Scale=42025.10 | 10.26 | 79.55 | 0 | 0 | |
| Phased DMDSampling Steps=4, Guidance Scale=12025.10 | 9.3 | 82.27 | 47.24 | 700.9 | |
| DMD2Sampling Steps=4, Guidance Scale=12025.10 | 3.23 | 65.45 | 55.7 | 763.1 |