A guitarist plucks an open string producing a low note, then presses down higher up the neck and plucks again, producing a much higher note.
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 guitarist
- a guitar
Event: a guitarist plucks a guitar string
Audio presence
- a guitar
Sound: a plucked guitar note
Key standards
Visual physical commonsense (V-PC)
- The guitarist plucks a single string twice: once with no fingers pressing the neck (open string), and once after one or more fingers press down higher up the neck.
Audio physical commonsense (A-PC)
- The second plucked note has a noticeably higher pitch than the first plucked note.
Cross-modal physical commonsense (AV-PC)
- Each plucked note onset aligns in time with a visible pluck of the guitar string.
- The pluck that produces the higher pitch aligns in time with the visible fingering higher up the neck; the lower pitch aligns with fingering on an open string or lower on the neck.