A ukulele is strummed, producing bright high-pitched chords. Then a bass guitar is strummed, producing deep low-pitched notes.
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 ukulele
- a bass guitar
Event: a ukulele and a bass guitar are played
Audio presence
- a ukulele
- a bass guitar
Sound: ['ukulele strum', 'bass guitar strum']
Key standards
Visual physical commonsense (V-PC)
- A small short-neck four-string ukulele is visibly played first, and a long-neck bass guitar is visibly played second.
Audio physical commonsense (A-PC)
- The bass guitar notes carry a noticeably lower pitch than the ukulele chords.
- The ukulele's strum has the bright mid-range chord timbre of a small four-string ukulele.
- The bass guitar's strum has the deep resonant bass timbre of a long-neck bass.
Cross-modal physical commonsense (AV-PC)
- Each strum sound aligns in time with a visible strum of its corresponding instrument.
- The higher-pitched strum corresponds to the smaller ukulele.
- The deeper strum corresponds to the long-necked bass guitar.