A pianist presses a key in close-up. The note begins at the precise moment the key reaches its lowest point.
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 pianist
- a piano key
Event: a finger presses a piano key
Audio presence
- a piano
Sound: a piano note
Key standards
Visual physical commonsense (V-PC)
- A pianist's finger presses a single piano key in close-up, with the key visibly depressing smoothly to its lowest point in continuous physically plausible motion.
Audio physical commonsense (A-PC)
- The audible note has the clear tonal attack and natural sustain of a real piano.
Cross-modal physical commonsense (AV-PC)
- The audible piano-note onset coincides in time with the visible moment the key reaches its lowest point.
- Each audible piano-note onset corresponds in time to a visible new strike of a piano key.