Text-to-Video Generation on 200-sequence multi-cultural benchmark
4.82NC ScoreUnityShots (I2V)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| UnityShots (I2V)Frame source=Nano Banana2026.06 | 4.82 | — | — | 5 | 5 | |
| UnityShots (I2V)Frame source=Qwen Image2026.06 | 4.82 | — | — | 4.93 | 4.96 | |
| MOVAFrame source=Nano Banana2026.06 | 4.78 | — | — | 4.55 | 4.91 | |
| MOVAFrame source=Qwen Image2026.06 | 4.75 | — | — | 4.45 | 4.81 | |
| OVIFrame source=Nano Banana2026.06 | 4.55 | — | — | 4.36 | 5 | |
| OVIFrame source=Qwen Image2026.06 | 4.52 | — | — | 4.27 | 4.89 | |
| ID-LoRAFrame source=Nano Banana2026.06 | 4.47 | — | — | 4.36 | 4.73 | |
| ID-LoRAFrame source=Qwen Image2026.06 | 4.45 | — | — | 4.27 | 4.64 | |
| LTX-2Frame source=Nano Banana2026.06 | 4.19 | — | — | 3.82 | 4.45 | |
| LTX-2Frame source=Qwen Image2026.06 | 4.17 | — | — | 3.73 | 4.36 |