A street performer plays a quiet acoustic guitar. A fire truck passes with its siren blaring, and the guitar is totally covered by the siren.
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 street performer
- an acoustic guitar
- a fire truck
- a street
Event: a street performer plays an acoustic guitar while a fire truck passes
Audio presence
- an acoustic guitar
- a fire truck siren
Sound: ['acoustic guitar', 'fire truck siren']
Key standards
Visual physical commonsense (V-PC)
- The fire truck moves past on the street with continuous motion, and the performer remains visibly playing the guitar with both hands throughout.
Audio physical commonsense (A-PC)
- The fire truck siren is louder than the guitar and is audibly recognizable as a siren while the truck passes.
Cross-modal physical commonsense (AV-PC)
- The period during which the guitar becomes inaudible aligns in time with the visible passage of the fire truck.