First-person view pushing a shopping cart through a supermarket, the wheels rattling on the tile floor. A PA announcement comes through ceiling speakers: "Attention shoppers, fresh strawberries are now half price in aisle three."
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 shopping cart
- a supermarket
- a tile floor
Event: a shopping cart is pushed through a supermarket
Audio presence
- a shopping cart
- ceiling speakers
Sound: ['cart wheels on tile', 'PA announcement']
Key standards
Visual physical commonsense (V-PC)
- The view is first-person POV from the cart-pusher's perspective.
- The first-person actor visibly pushes the cart, with hands or arms on the cart handle and the cart moving with the camera.
Audio physical commonsense (A-PC)
- The cart wheels carry the natural rattle timbre of hard wheels rolling on tile flooring throughout the cart's visible motion.
- The PA announcement carries the band-limited compressed and slightly reverberant timbre of overhead ceiling speakers in a large retail space.
Cross-modal physical commonsense (AV-PC)
- The cart rattle originates from the visible cart wheels rolling on the tile floor.
- The PA announcement originates from overhead PA speakers consistent with the visible supermarket space.