Text+Reference+Audio-to-Video (RA2V) Generation on HOIVG-Bench 1.0 (test)
8.146Temporal Alignment (TA)HuMo
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| HuMoparameters=17B2026.04 | 8.146 | 0.805 | 0.344 | 8.013 | 8.316 | 0.439 | 0.739 | 10.27 | 4.269 | |
| OmniShow2026.04 | 8.093 | 0.81 | 0.369 | 8.612 | 7.608 | 0.465 | 0.742 | 10.86 | 5.554 | |
| HuMoparameters=1.7B2026.04 | 7.489 | 0.575 | 0.329 | 7.234 | 9.117 | 0.428 | 0.731 | 9.97 | 4.182 | |
| HunyuanCustom2026.04 | 7.289 | 0.457 | 0.35 | 6.072 | 10.08 | 0.439 | 0.715 | 9.15 | 3.658 |