A singer holds a long note inside a stone chapel. After each held note, a warm sustained echo lingers around the room before fading.
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 singer
- a stone chapel
Event: a singer holds a note inside a chapel
Audio presence
- a singer
Sound: a sustained sung note
Key standards
Visual physical commonsense (V-PC)
- A single visible singer is shown inside a stone chapel.
- The singer holds one long sustained note rather than a melody.
Audio physical commonsense (A-PC)
- The held note carries a warm sustained reverberation tail that lingers and then fades.
- The reverberation is consistent with reflections in a stone chapel.
Cross-modal physical commonsense (AV-PC)
- The held note in the audio aligns in time with the singer's visibly held mouth posture.
- The voice in the audio originates from the singer visibly performing in the chapel.