← all videos

First-person view inside a crowded bar at night. A jukebox in the corner plays a rock song, mixing with the room's echo, clinking glasses, and overlapping conversations.

C1-2-18 Steady State · source_anchoring 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 jukebox
  • a bar interior
  • glasses
  • a crowd

Event: a first-person view inside a bar with a jukebox

Audio presence

  • a jukebox
  • glasses
  • a crowd

Sound: ['rock music from a jukebox', 'clinking glasses', 'overlapping conversations']

Key standards

Visual physical commonsense (V-PC)

  • The view is first-person POV inside a recognizable bar interior.
  • A jukebox is visible somewhere in the frame at some point in the clip.

Audio physical commonsense (A-PC)

  • The music is rock-style with audible bar-room reverb and is present throughout the clip.
  • The bar ambient mix is audibly present, including clinking glasses, crowd murmur, and overlapping conversations.

Cross-modal physical commonsense (AV-PC)

  • The rock music originates from the visible jukebox in the bar.