A close-up shows hands rhythmically striking a conga drum, but every hand impact produces a sharp, crisp snare-drum hit perfectly synchronized to the contact, as if the conga itself were generating snare sounds.
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
- hands
- a conga drum
Event: hands rhythmically strike a conga drum
Audio presence
- a conga drum
Sound: snare drum hits
Key standards
Visual physical commonsense (V-PC)
- A conga drum is clearly visible and is rhythmically struck by hands in close-up with continuous physically plausible drumming motion.
- The instrument remains a recognizable conga drum throughout the clip with its tall narrow open-bottom shell, without morphing into a snare drum or any other instrument.
Audio physical commonsense (A-PC)
- Each hand impact produces a sharp crisp snare-drum hit with the rattling wire-snare buzz of a real snare drum, rather than the deep open-tone or slap timbre of a conga.
Cross-modal physical commonsense (AV-PC)
- Each snare-drum hit aligns in time with a visible hand impact on the conga drumhead.