Text-to-Video Generation on VBench original prompts (test)
83.75Total ScoreBase Model-720p
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Base Model-720pNFE=50×2, Speedup=1.0×, Backbone=Wan2.1-T2V-14B2026.03 | 83.75 | 85.44 | 76.95 | |
| RMDNFE=3 + 3, Speedup=25.6×, Backbone=Wan2.1-T2V-14B2026.03 | 82.51 | 84.37 | 75.05 | |
| TDMNFE=6, Speedup=16.7×, Backbone=Wan2.1-T2V-14B2026.03 | 80.48 | 81.85 | 75 | |
| DMD2NFE=6, Speedup=16.7×, Backbone=Wan2.1-T2V-14B2026.03 | 80.3 | 81.98 | 73.6 |