A crowd cheers inside a packed stadium with sharp clapping, whistles, and a roaring wash. The scene cuts to a parking lot outside, where only a muffled low wash carries 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 crowd
- a stadium
- a parking lot
Event: a crowd cheers in a stadium
Audio presence
- a crowd
Sound: crowd cheering
Key standards
Visual physical commonsense (V-PC)
- A scene inside a packed stadium is shown, and a separate exterior scene shows a parking lot with cars visible.
Audio physical commonsense (A-PC)
- In the parking-lot scene the sharp clapping and whistles are noticeably attenuated while a low-frequency muffled crowd wash carries through.
Cross-modal physical commonsense (AV-PC)
- The audible spectral character of the crowd matches the visible interior or exterior vantage of each scene.