SAME-PROMPT BENCHMARK · AUGUST 2026
Best AI Video Model for 人体运动
舞者、运动员、逼真的人物动作. We gave five models the identical brief on ManifoldGen — here are the actual generations, ranked.
THE EXACT PROMPT EVERY MODEL RAN
A dancer in a flowing red dress performs contemporary dance on a rain-slicked city street at night, neon reflections on wet pavement, slow-motion fabric trails, cinematic tracking shot
THE REST OF THE FIELD — SAME PROMPT
generation pending
generation pending
| RANK | MODEL | WHY IT PLACED HERE | MEDIAN SPEED* |
|---|---|---|---|
| 1 | Seedance 2 | 布料动态和脚步最干净；霓虹反射保持物理合理。 | — |
| 2 | Manifold H3 | 姿势变化富有表现力，手部细节略柔和。 | 264s |
| 3 | Wan | 节奏扎实，但姿势之间的过渡较生硬。 | — |
| 4 | LTX 2 | 动作清晰，快速旋转时肢体有轻微拖影。 | 65s |
| 5 | Seedance 2 Fast | 同一场景的快速草稿，动作细节较少。 | — |
*Median wall-clock time across this model's completed runs in our harness. Placements are editorial calls made from these exact generations — watch the clips above and disagree with us. Generations for this category are still running.
Making human motion shots?
Paste your prompt into ManifoldGen. One subscription, every model — pick the winner yourself or let routing do it.