A person walks up wooden stairs with warm hollow footsteps. Then walks onto a metal staircase, and each footfall rings brighter and more metallic.
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 person
- wooden stairs
- a metal staircase
Event: a person walks up stairs
Audio presence
- footsteps
Sound: footstep impacts
Key standards
Visual physical commonsense (V-PC)
- The person walks up both a wooden staircase and a metal staircase within the clip, with natural gait and plausible foot placement on each.
Audio physical commonsense (A-PC)
- The wooden-stair footsteps have a warm hollow timbre and the metal-stair footfalls have a distinctly brighter, more metallic ringing timbre.
Cross-modal physical commonsense (AV-PC)
- Each footstep sound coincides in time with a visible foot landing on its corresponding surface.
- The warm hollow timbre corresponds to footsteps on the wooden staircase.
- The brighter, more metallic ringing corresponds to footsteps on the metal staircase.