Text-to-Video generation on MovieGenBench 81 frames, 256x256
29.8URWan 2.2 VAE
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Wan 2.2 VAECPR=(16 × 16 × 4), Chn=48, Backbone=MMDiT 1.3B2025.12 | 29.8 | 23.1 | 600 | |
| SSVAECPR=(16 × 16 × 4), Chn=48, Backbone=MMDiT 1.3B2025.12 | 31.6 | 24.5 | 484 |