A marching band plays a few meters away with crisp cymbals and sharp flutes over pounding bass drums. The scene cuts to several blocks away, where only the bass drum and tuba carry through.
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 marching band
- cymbals
- flutes
- bass drums
- a street
Event: a marching band plays on a street
Audio presence
- a marching band
Sound: marching band music
Key standards
Visual physical commonsense (V-PC)
- A near-scene shows a marching band actively performing with instruments held and visibly played, and a separate scene shows the same band visibly several blocks away.
Audio physical commonsense (A-PC)
- In the distant scene the high-frequency cymbals and flutes are noticeably attenuated while the low-frequency bass drum and tuba carry through.
Cross-modal physical commonsense (AV-PC)
- The audible instrument spectral mix matches the visible proximity of the band in each scene.