A wide shot of ocean waves crashing against rocks. Wind and surf dominate the soundscape. A documentary voice says, "Coastlines are shaped by repetition, not force."
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
- ocean waves
- rocks
- a coastline
Event: ocean waves crash against rocks
Audio presence
- ocean waves
- wind
- a narrator
Sound: ['crashing waves', 'wind', 'a documentary voice']
Key standards
Visual physical commonsense (V-PC)
- Ocean waves visibly crash against rocks at a coastline with realistic impact behavior.
Audio physical commonsense (A-PC)
- The documentary voice is clean and dry with studio-recording quality and no room reverberation.
Cross-modal physical commonsense (AV-PC)
- The documentary voice plays as a non-diegetic overlay with no visible source in the scene.