A foot steps onto a pile of wet leaves. The sound is a dull muffled rustle with little cracking.
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
- wet leaves
Event: a foot steps onto wet leaves
Audio presence
- wet leaves
Sound: wet leaves compressing
Key standards
Visual physical commonsense (V-PC)
- The leaves under the foot appear visibly damp and matted, with water droplets, darker colour, or sticking together as in a puddle.
Audio physical commonsense (A-PC)
- The sound is a dull, muffled rustle with little cracking, consistent with wet leaves too damp to snap.
Cross-modal physical commonsense (AV-PC)
- The muffled rustle onset aligns in time with the visible foot contact on the wet leaves.