A first-person walk along a sidewalk. Cars pass, footsteps move, and distant city noise fills the space. A subtle electronic background music plays steadily.
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 sidewalk
- cars
- a city
Event: a first-person walk along a sidewalk
Audio presence
- cars
- a pedestrian
- a city
- background music
Sound: ['passing cars', 'footsteps', 'distant city noise', 'electronic background music']
Key standards
Visual physical commonsense (V-PC)
- The view is first-person POV walking along a sidewalk.
- Cars are visibly passing with physically plausible form throughout the clip.
Audio physical commonsense (A-PC)
- Electronic background music is clearly audibly present, studio-produced and clean.
Cross-modal physical commonsense (AV-PC)
- The electronic background music plays as a non-diegetic overlay with no visible source in the scene.