A wooden stick taps a thick aluminum plate with a firm solid sound, then strikes a thin aluminum can. The sound becomes lighter, thinner, and rattly.
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 wooden stick
- an aluminum plate
- an aluminum can
Event: a wooden stick strikes an aluminum plate and an aluminum can
Audio presence
- an aluminum plate
- an aluminum can
Sound: stick strike on aluminum
Key standards
Visual physical commonsense (V-PC)
- The stick makes visible contact with both the aluminum plate and the aluminum can in sequence.
Audio physical commonsense (A-PC)
- The plate strike has a firm, solid, thick-metal timbre.
- The can strike has a lighter, thinner, rattly thin-metal timbre with no unnatural long sustain.
Cross-modal physical commonsense (AV-PC)
- The plate strike sound coincides in time with the visible stick contact on the aluminum plate.
- The can strike sound coincides in time with the visible stick contact on the aluminum can.