← all videos

A large floor tom is struck, producing a deep boom. Then a small snare drum is struck, producing a sharp high crack.

C2-1-13 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 floor tom
  • a snare drum

Event: a floor tom and a snare drum are struck

Audio presence

  • a floor tom
  • a snare drum

Sound: ['a floor tom boom', 'a snare drum crack']

Key standards

Visual physical commonsense (V-PC)

  • A larger floor-tom-style drum is visibly struck first, and a clearly smaller snare-style drum is visibly struck second.

Audio physical commonsense (A-PC)

  • The snare drum crack is noticeably higher in pitch than the floor tom's deep boom.
  • Each hit has the characteristic drumhead-impact timbre of a struck drum.

Cross-modal physical commonsense (AV-PC)

  • Each drum hit sound aligns in time with a visible strike on the corresponding drum.
  • The higher-pitched crack corresponds to the visibly smaller snare.
  • The deeper boom corresponds to the larger floor tom.