A vibrating tuning fork is held near a small candle flame. The flame visibly flickers and bends back and forth in time with the buzzing sound.
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 tuning fork
- a candle flame
Event: a tuning fork is held near a candle flame
Audio presence
- a tuning fork
Sound: a tuning fork buzz
Key standards
Visual physical commonsense (V-PC)
- A canonical U-tine tuning fork is held vibrating in the air near a candle flame.
- The fork hovers in the air at a small distance from the flame and stays intact throughout the clip.
Audio physical commonsense (A-PC)
- The fork produces a clear sustained tone at a stable fundamental pitch.
- The fork tone is loud enough to be distinctly audible in the audio.
Cross-modal physical commonsense (AV-PC)
- The flame visibly flickers and bends while the fork is vibrating near it.
- The flame's flicker oscillation is synchronized in time with the audible buzzing of the fork.