← all videos

A large ceramic bowl is tapped, producing a low warm tone. Then a small ceramic bowl is tapped, producing a noticeably higher ring.

C2-1-14 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 ceramic bowl
  • a small ceramic bowl

Event: a ceramic bowl is tapped

Audio presence

  • a ceramic bowl

Sound: a ceramic bowl tap

Key standards

Visual physical commonsense (V-PC)

  • A larger ceramic bowl is tapped first, and a clearly smaller ceramic bowl is tapped second, with each tap visibly contacting its bowl.

Audio physical commonsense (A-PC)

  • The small bowl's ring is noticeably higher in pitch than the large bowl's low warm tone.
  • Each tap has the short-decay bright ring of a struck ceramic bowl.

Cross-modal physical commonsense (AV-PC)

  • Each tap sound aligns in time with a visible tap on the corresponding bowl.
  • The higher-pitched tap corresponds to the visibly smaller bowl.
  • The lower warm tone corresponds to the visibly larger bowl.