A gentle stream trickles over pebbles with a soft babble. The scene cuts to a massive waterfall roaring thunderously.
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 stream
- pebbles
- a waterfall
Event: a stream and a waterfall flow
Audio presence
- a stream
- a waterfall
Sound: flowing water
Key standards
Visual physical commonsense (V-PC)
- The clip shows both a small stream trickling over pebbles and, after a scene cut, a large waterfall.
Audio physical commonsense (A-PC)
- The waterfall roar is noticeably louder than the gentle stream babble.
- The audio shifts between two distinct loudness states across the scene cut, from a quiet stream babble to a loud waterfall roar.
Cross-modal physical commonsense (AV-PC)
- The soft babble aligns with the stream scene.
- The thunderous roar aligns with the waterfall scene.