A wooden stick taps a plastic bag repeatedly. Each tap produces a dry crinkly crackle, light and hollow with no ringing.
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
- a plastic bag
Event: a wooden stick taps a plastic bag
Audio presence
- a plastic bag
Sound: stick tapping plastic bag
Key standards
Visual physical commonsense (V-PC)
- A single wooden stick visibly taps a plastic bag and the bag deforms or crinkles on each contact.
Audio physical commonsense (A-PC)
- Each tap is a dry crinkly crackle that is light and hollow with no ringing.
Cross-modal physical commonsense (AV-PC)
- Each crackle onset aligns in time with a visible tap of the stick on the bag.