First-person (egocentric) view of a train departing straight away from the camera on a platform, the camera stationary as the train recedes into the distance. Despite moving away, the train's sound pitch intentionally increases over time.
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 train
- a station platform
Event: a train recedes from a stationary first-person camera on a platform
Audio presence
- a train
Sound: train engine sound
Key standards
Visual physical commonsense (V-PC)
- A visible train moves continuously straight away from the stationary first-person camera, receding into the distance throughout the clip.
Audio physical commonsense (A-PC)
- A continuous train sound with the engine and wheel-on-track character of a real train is audible throughout the clip.
- The pitch of the train sound rises noticeably and continuously from the start of the clip to the end.
Cross-modal physical commonsense (AV-PC)
- The continuous rise in train sound pitch aligns in time with the train's visible recession from the camera.