← all videos

A large dog barks with a deep booming sound, then a small dog barks back with a high sharp yap.

C2-1-11 Event Transition · source_body principle: Object Size -> Pitch (Mechanics)
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 large dog
  • a small dog

Event: a large dog and a small dog bark

Audio presence

  • a large dog
  • a small dog

Sound: ['a large dog bark', 'a small dog yap']

Key standards

Visual physical commonsense (V-PC)

  • Both the large dog and the small dog visibly vocalize in the clip, one after the other.
  • Both dogs are real live-action dogs of clearly different sizes.

Audio physical commonsense (A-PC)

  • The small dog's yap is noticeably higher in pitch than the large dog's deep booming bark.

Cross-modal physical commonsense (AV-PC)

  • Each bark aligns in time with the corresponding dog's visible vocalization.
  • The higher-pitched bark corresponds to the smaller dog.
  • The deeper booming bark corresponds to the larger dog.