A person claps their hands at close range. The visible palm contact and the audible clap happen at exactly the same instant.
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 person
- two hands
Event: a person claps their hands
Audio presence
- two hands
Sound: a hand clap
Key standards
Visual physical commonsense (V-PC)
- A visible person performs hand claps with their own two hands meeting in continuous physically plausible motion.
Audio physical commonsense (A-PC)
- Each audible clap has the sharp percussive slap character of two human hands meeting.
Cross-modal physical commonsense (AV-PC)
- Each visible palm-contact moment in the clip coincides in time with an audible clap onset.
- Each audible clap onset in the clip coincides in time with a visible palm-contact moment.