Text+Reference-to-Video (R2V) Generation on HOIVG-Bench 1.0 (test)
8.609TAPhantom
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Phantomparameters=14B2026.04 | 8.609 | 0.876 | 0.366 | 0.449 | 0.741 | 10.93 | 5.517 | |
| VACE2026.04 | 8.413 | 0.759 | 0.368 | 0.457 | 0.722 | 10.72 | 5.442 | |
| Phantomparameters=1.3B2026.04 | 8.342 | 0.708 | 0.351 | 0.459 | 0.722 | 10.9 | 5.637 | |
| HuMoparameters=17B2026.04 | 7.949 | 0.843 | 0.346 | 0.448 | 0.726 | 9.97 | 3.685 | |
| OmniShow2026.04 | 7.746 | 0.874 | 0.389 | 0.468 | 0.74 | 11.12 | 5.885 | |
| HunyuanCustom2026.04 | 7.523 | 0.44 | 0.359 | 0.452 | 0.697 | 10.11 | 5.286 | |
| HuMoparameters=1.7B2026.04 | 7.087 | 0.647 | 0.333 | 0.441 | 0.723 | 9.76 | 3.406 |