← all videos

A large temple bell is struck, producing a deep sustained ring. Then a small handheld bell is struck, producing a bright high-pitched tinkle.

C2-1-12 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 temple bell
  • a small handheld bell

Event: a temple bell and a handheld bell are struck

Audio presence

  • a temple bell
  • a handheld bell

Sound: ['a temple bell ring', 'a handheld bell tinkle']

Key standards

Visual physical commonsense (V-PC)

  • The large temple bell is visibly struck directly on the bell itself.
  • A separate, clearly smaller handheld bell is also visibly struck in the clip.

Audio physical commonsense (A-PC)

  • The small handheld bell's tinkle is noticeably higher in pitch than the large temple bell's deep ring.
  • Each strike sound has the bright sustained metallic ring of a real bell.

Cross-modal physical commonsense (AV-PC)

  • Each bell ring sound aligns in time with a visible strike on the corresponding bell.
  • The higher-pitched ring corresponds to the smaller handheld bell.
  • The deeper sustained ring corresponds to the larger temple bell.