An ice cream truck plays its jingle as it drives through a neighborhood. The melody is bright nearby and fades as the truck drives away.
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
- an ice cream truck
- a neighborhood street
Event: an ice cream truck drives through a neighborhood
Audio presence
- an ice cream truck
Sound: an ice cream truck jingle
Key standards
Visual physical commonsense (V-PC)
- The ice cream truck drives steadily down the street with continuous forward motion, shrinking naturally in the frame as the clip progresses.
Audio physical commonsense (A-PC)
- A recognizable ice-cream-truck melody plays from the truck and fades steadily quieter as the truck drives away.
Cross-modal physical commonsense (AV-PC)
- The decrease in jingle loudness corresponds to the truck's decreasing visible size in the frame.