SAME-PROMPT BENCHMARK · AUGUST 2026
Best AI Video Model for 风格化世界
动漫、纸艺、动态插画. We gave five models the identical brief on ManifoldGen — here are the actual generations, ranked.
THE EXACT PROMPT EVERY MODEL RAN
A paper-craft origami fox trots through a miniature cardboard forest, tiny paper leaves drift through the air, tilt-shift macro lens, warm afternoon light
THE REST OF THE FIELD — SAME PROMPT
generation pending
generation pending
generation pending
| RANK | MODEL | WHY IT PLACED HERE | MEDIAN SPEED* |
|---|---|---|---|
| 1 | LTX 2 | 材质感迷人：纸张纹理、移轴虚化、俏皮的步态。 | 65s |
| 2 | Manifold H3 | 丰富的微缩世界构建；狐狸设计在镜头间漂移。 | 264s |
| 3 | Seedance 2 Fast | 草稿成本下构图整洁。 | — |
| 4 | Seedance 2 | 渲染精致，对需求的理解更直白。 | — |
| 5 | Wan | 场景可读，但材质触感最弱。 | — |
*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.
Making stylized world shots?
Paste your prompt into ManifoldGen. One subscription, every model — pick the winner yourself or let routing do it.