Text-to-Video generation on Movie 81 frames, 256x256 (val)
40.8URSSVAE
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SSVAECPR=(16 × 16 × 4), Chn=48, Backbone=MMDiT 1.3B2025.12 | 40.8 | 36.8 | 272 | |
| Wan 2.2 VAECPR=(16 × 16 × 4), Chn=48, Backbone=MMDiT 1.3B2025.12 | 40.1 | 35.2 | 247 |