← all videos

I wear over-ear headphones in a quiet room, and the music sounds full and rich. Then I take them off and set them on the desk, and the music shrinks to a tiny tinny leak.

C2-2-23 Event Transition · source_excitation principle: Diegetic Sound (Wave)
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 person
  • over-ear headphones
  • a desk

Event: a person removes headphones and sets them on a desk

Audio presence

  • headphones

Sound: music from headphones

Key standards

Visual physical commonsense (V-PC)

  • The over-ear headphones remain headphones throughout the clip, keeping the same over-ear cup form factor before and after removal.
  • The person removes the headphones from the head and sets them down on the desk.

Audio physical commonsense (A-PC)

  • The music sounds full and rich while the headphones are worn on the head.
  • After the headphones are placed on the desk, the same music continues at reduced bandwidth and reduced loudness as a thin tinny leak.

Cross-modal physical commonsense (AV-PC)

  • The music originates from the visible headphones in the scene.
  • The shift from full music to thin tinny leak occurs at or shortly after the visible removal action.