MiniMax-H3提示词

For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.

integrated_multimodal_description: [Shot 1] Live-action, cinematic, the young man shown in <Picture 1> remains seated on the black leather sofa in the bar, preserving his wavy dark hair, denim jacket over beige knit sweater, silver necklace, black trousers, the red wine glass in his right hand, the black smartphone in his left hand, and the warm-lit bar background with bottles and glasses. The camera holds a steady medium shot. A relaxed, contented expression settles on his face as he lifts the wine glass to his lips and takes a slow, casual sip of red wine. He lowers the glass slightly and turns his gaze down toward the smartphone in his left hand, the screen facing him. His eyes gradually widen as he watches something on the screen, his eyebrows lifting and his expression shifting from casual interest to growing surprise and excitement.

[Shot 2] At 00:05.000, the camera cuts to a slightly tighter medium shot. The man freezes for a full second, eyes locked on the phone screen in stunned excitement. Then he casually tosses the wine glass aside onto the leather sofa cushion beside him, the red wine sloshing inside the glass. He brings both hands to the smartphone, holding it with both hands now, leaning forward slightly with renewed energy. The young man with an excited, enthusiastic voice (S1) exclaims: <d>[Chinese] 卧靠，这视频真不错</d> with a wide, amazed grin spreading across his face.

overall_soundscape: Soft bar ambience with muted background music and distant glass clinks. The subtle sound of wine being sipped. The soft thud of the wine glass landing on the leather sofa. Faint tapping sounds as his fingers interact with the phone screen.

non_diegetic_music: N/A

For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.

integrated_multimodal_description: [Shot 1] Live-action, cinematic, the young man shown in <Picture 1> remains seated on the black leather sofa in the bar, preserving his wavy dark hair, denim jacket over beige knit sweater, silver necklace, black trousers, the red wine glass in his right hand, the black smartphone in his left hand, and the warm-lit bar background with bottles and glasses. The camera holds a steady medium shot. A relaxed, contented expression settles on his face as he lifts the wine glass to his lips and takes a slow, casual sip of red wine. He lowers the glass slightly and turns his gaze down toward the smartphone in his left hand, the screen facing him. His eyes gradually widen as he watches something on the screen, his eyebrows lifting and his expression shifting from casual interest to growing surprise and excitement.

[Shot 2] At 00:05.000, the camera cuts to a slightly tighter medium shot. The man freezes for a full second, eyes locked on the phone screen in stunned excitement. Then he casually tosses the wine glass aside onto the leather sofa cushion beside him, the red wine sloshing inside the glass. He brings both hands to the smartphone, holding it with both hands now, leaning forward slightly with renewed energy. The young man with an excited, enthusiastic voice (S1) exclaims: <d>[Chinese] 卧靠，这视频真不错</d> with a wide, amazed grin spreading across his face.

overall_soundscape: Soft bar ambience with muted background music and distant glass clinks. The subtle sound of wine being sipped. The soft thud of the wine glass landing on the leather sofa. Faint tapping sounds as his fingers interact with the phone screen.

non_diegetic_music: N/A