A foot steps onto a pile of dry leaves. The sound is crisp and brittle, with many sharp crackles at once.
Seedance 2.0ByteDance · proprietary
Kling 3.0 OmniKuaishou · proprietary
Veo 3.1Google · proprietary
LTX-2.3Lightricks · open
Ovi 1.1character.ai · open
JavisDiT++JavisDiT · open
MagiHumanGAIR-NLP · open
Per-prompt rubric
Basic standards
Visual presence
- a foot
- dry leaves
Event: a foot steps onto dry leaves
Audio presence
- dry leaves
Sound: dry leaves crushing
Key standards
Visual physical commonsense (V-PC)
- The pile under the foot consists of dry leaves, and the leaves compress and scatter under the foot in a physically plausible way.
Audio physical commonsense (A-PC)
- The sound is crisp, brittle crackling with many sharp simultaneous crackles consistent with dry leaves being crushed.
Cross-modal physical commonsense (AV-PC)
- The crackling onset aligns in time with the visible foot contact on the leaves.