{
"source": "大梁仙朝·第一章 义庄少年",
"style": "realistic",
"promptLang": "en",
"params": {
"maxSegmentSeconds": 15,
"minCutSeconds": 2,
"maxCutSeconds": 5,
"maxOnScreen": 3,
"tolerance": 0.15
},
"episodes": [
{
"ep": 1,
"segments": [
{
"id": "E01-01",
"sceneIndex": 1,
"cuts": [
{
"beats": [
1,
2
],
"seconds": 4,
"size": "medium",
"camera": "Tracking Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of a sixteen-year-old Chinese youth in a plain gray robe squatting in a traditional Chinese mortuary courtyard, a hand plane pushing across a pine plank, wood shavings curling onto the ground, late afternoon golden light filtering through old wooden beams, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
3,
4
],
"seconds": 4,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth finishing the last stroke of his hand plane, looking up at the sky, the sun setting behind the courtyard wall, then gathering wood shavings into the corner, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
5,
5
],
"seconds": 3,
"size": "close",
"camera": "Push In",
"characters": [
"C01"
],
"props": [],
"frame": "close-up of the youth standing up and wiping his hands on his pant leg, a pile of wood shavings in the corner, sunset light catching the edge of his hand, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 4.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 8.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A tracking shot follows the youth as he squats in the courtyard, his hand plane pushing across a pine plank, wood shavings curling onto the ground with each rhythmic stroke.\n[Shot 2] At 00:04.000, the camera cuts to a static shot in medium framing: the youth finishes the last stroke, looks up at the sky as the sun sets behind the courtyard wall, then gathers the wood shavings into the corner.\n[Shot 3] At 00:08.000, the camera cuts to a close-up with a slow push in: the youth stands up and wipes his hands on his pant leg, the pile of shavings in the corner.\n\noverall_soundscape: A rhythmic rasp of the hand plane gliding across wood, wood shavings clatter softly onto the ground, and a late afternoon breeze stirs in the courtyard.\n\nnon_diegetic_music: N/A"
},
{
"id": "E01-02",
"sceneIndex": 1,
"cuts": [
{
"beats": [
6,
7
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "medium shot of a weathered fifty-year-old man in a dark robe leaning against the courtyard wall, calling out with a rough voice, wood shavings on the ground beside him, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
8,
10
],
"seconds": 5,
"size": "wide",
"camera": "Tracking Shot",
"characters": [
"C01",
"C02"
],
"props": [],
"frame": "wide shot of the courtyard as the youth wipes his hands and walks toward the hall door, the old man watching from the wall, wood shavings underfoot, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. The old man leans against the courtyard wall in a static shot in medium framing, his rough voice carrying across the yard: [Chinese] 阿砚，吃饭了。 He adds with a grunt: [Chinese] 今儿有腊肉，你王叔送来的。\n[Shot 2] At 00:05.000, the camera cuts to a tracking shot in wide framing: the youth responds with [Chinese] 来了。 and the old man watches as the youth wipes his hands and walks toward the hall door, wood shavings crunching underfoot.\n\noverall_soundscape: Wood shavings crunch underfoot, the distant creak of the mortuary's old wooden gates, and the rough voice echoing off courtyard walls.\n\nnon_diegetic_music: N/A"
},
{
"id": "E01-03",
"sceneIndex": 2,
"cuts": [
{
"beats": [
1,
3
],
"seconds": 4,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C02"
],
"props": [],
"frame": "medium shot of a dim wooden hall lit by a single oil lamp, a weathered man placing a piece of cured pork into the youth's bowl while eating plain rice himself, a dark wooden table between them, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
4,
5
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth lifting his bowl, speaking with quiet gratitude under the oil lamp's warm glow, the man's bowl visible in the foreground, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
6,
6
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "close-up of the weathered man's face, his crinkled eyes smiling as he nods, oil lamp light flickering on his weathered skin, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 4.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds on the dim hall: the old man places a piece of cured pork into the youth's bowl, then settles back to eat plain rice, the oil lamp flickering above.\n[Shot 2] At 00:04.000, the camera cuts to a static shot in medium framing of the youth: he lifts his bowl and speaks with quiet gratitude, the young man with a soft, uncomplaining voice (S1) says: [Chinese] 爹，吃什么苦？ Then: [Chinese] 有腊肉吃，算不得苦。\n[Shot 3] At 00:09.000, the camera cuts to a close-up static shot: the old man's crinkled eyes smile, he nods, the oil lamp flickering on his weathered skin.\n\noverall_soundscape: Porcelain bowl clinks against a wooden table, rice grains shifting in a ceramic bowl, and the faint hiss of the oil lamp wick.\n\nnon_diegetic_music: N/A"
},
{
"id": "E01-04",
"sceneIndex": 2,
"cuts": [
{
"beats": [
7,
9
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "medium shot of the old man eating silently, pushing a small dish of pickles toward the young man, the oil lamp flame swaying in a draft, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
10,
11
],
"seconds": 5,
"size": "close",
"camera": "Push In",
"characters": [
"C01"
],
"props": [
"P02"
],
"frame": "close-up of the youth's gaze rising to the wall, a faded embroidered cloth hanging there with a plum blossom stitched at the corner, a slow push in toward the cloth, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
12,
12
],
"seconds": 4,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C03"
],
"props": [],
"frame": "medium shot of a flashback scene: a mute young woman in period clothing seated by a lamplight, an embroidery needle between her fingers, her lips sealed, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the old man eats silently, pushes a small dish of pickles toward the youth, the oil lamp flame swaying in a draft.\n[Shot 2] At 00:05.000, the camera cuts to a close-up with a slow push in: the youth's gaze rises to the wall where a faded embroidered cloth hangs, a plum blossom stitched at the corner, the push in drawing attention to the embroidery.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in medium framing in flashback: a mute young woman in period clothing sits by lamplight, an embroidery needle between her fingers, her lips sealed, her expression gentle.\n\noverall_soundscape: A small dish clinks across the table, the oil lamp wick hisses, and the silence of memory pressing in.\n\nnon_diegetic_music: A single sparse piano note at a slow tempo, fading before the flashback begins."
},
{
"id": "E01-05",
"sceneIndex": 2,
"cuts": [
{
"beats": [
13,
13
],
"seconds": 3,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C03"
],
"props": [],
"frame": "medium shot of the mute young woman in flashback, her head tilting slightly, a faint smile crossing her lips, lamplight catching the embroidery needle, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
14,
15
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth back in the present, blinking as the flashback ends, his expression turning serious, the oil lamp flickering behind him, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
16,
17
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "close-up of the old man's hand pausing mid-meal, his face half-lit by the swaying oil lamp, his shadow stretching long across the wall, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
18,
19
],
"seconds": 3,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "medium shot of the old man, his voice rough, looking away from the youth, the oil lamp casting long shadows, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 3.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 8.00-second mark of the target video; Picture 4 (from Shot 4) aligns with the 12.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing in flashback: the mute young woman tilts her head, a faint smile crossing her lips, the lamplight catching the embroidery needle.\n[Shot 2] At 00:03.000, the camera cuts to a static shot in medium framing in the present: the youth blinks as the flashback fades, his expression turning serious, and the young man with a quiet, probing voice (S1) asks: [Chinese] 爹，娘当年到底是怎么死的？\n[Shot 3] At 00:08.000, the camera cuts to a close-up static shot: the old man's hand pauses mid-meal, his face half-lit by the swaying oil lamp, his shadow stretching long across the wall.\n[Shot 4] At 00:12.000, the camera cuts to a static shot in medium framing: the old man looks away, and the weathered old man with a rough, evasive voice (S2) mutters: [Chinese] 我说过，是妖祸。 Then adds: [Chinese] 吃饭吧。\n\noverall_soundscape: The oil lamp wick hisses and pops, a chopstick taps the rim of a bowl, and silence pressing in the hall.\n\nnon_diegetic_music: N/A"
},
{
"id": "E01-06",
"sceneIndex": 2,
"cuts": [
{
"beats": [
20,
21
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth lowering his gaze to eat, his hands gripping the bowl tightly, the oil lamp light dimming, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
22,
23
],
"seconds": 5,
"size": "wide",
"camera": "Static Shot",
"characters": [],
"props": [],
"frame": "wide shot of the dim hall, the oil lamp flame flickering, the wooden walls swaying between light and shadow, no figures visible, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the youth lowers his gaze to eat, his hands gripping the bowl tightly, the oil lamp light dimming.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in wide framing: the dim hall alone, the oil lamp flame flickering, the wooden walls swaying between light and shadow, no figures in frame.\n\noverall_soundscape: A bowl clinks softly, the oil lamp wick sputters, and the night wind presses against the windows.\n\nnon_diegetic_music: N/A"
},
{
"id": "E01-07",
"sceneIndex": 3,
"cuts": [
{
"beats": [
1,
3
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [
"P01"
],
"frame": "medium shot of the youth lying in a small dark bedroom, a green jade pendant clenched in his palm, his face half-lit by a distant oil lamp, the jade warming under his grip, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
4,
5
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [
"P01"
],
"frame": "close-up of the youth's closed eyelids, the jade pendant visible in his loose fist, a faint tremor passing through the jade, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
6,
6
],
"seconds": 3,
"size": "wide",
"camera": "Static Shot",
"characters": [],
"props": [],
"frame": "wide shot of the dark bedroom, the youth a still figure in bed, darkness beyond the window, no visible movement, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the youth lies in the dark bedroom, the green jade pendant clenched in his palm, his face half-lit by a distant oil lamp, the jade warming under his grip.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in close framing: the youth's closed eyelids, the jade visible in his loose fist, a faint tremor passing through the jade.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in wide framing: the dark bedroom, the youth a still figure in bed, darkness beyond the window, a distant dog bark barely audible.\n\noverall_soundscape: The faint creak of a wooden bed, a distant dog bark echoing through the night, and the silence of a sleeping house.\n\nnon_diegetic_music: A single low drone note at a very slow tempo, fading as the dog bark ends."
},
{
"id": "E01-08",
"sceneIndex": 3,
"cuts": [
{
"beats": [
7,
8
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the dark bedroom, the youth barely stirring in bed, the night wind pressing through window gaps, the oil lamp flame dimming, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
9,
10
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "close-up of the oil lamp flame dropping low, the youth's eyes snapping open in the dark, the lamp guttering, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
11,
12
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth sitting up in bed, staring at the dark window, his eyes wide, the room pitch dark beyond the lamp, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the dark bedroom, the youth barely stirring in bed, the night wind pressing through window gaps, the oil lamp flame dimming.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in close framing: the oil lamp flame dropping low, the youth's eyes snapping open in the dark, the lamp guttering.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in medium framing: the youth sitting up in bed, staring at the dark window, his eyes wide, the room pitch dark beyond the lamp.\n\noverall_soundscape: Wind hissing through window gaps, the oil lamp sputtering low, and the creak of the mortuary's courtyard gate.\n\nnon_diegetic_music: N/A"
},
{
"id": "E01-09",
"sceneIndex": 3,
"cuts": [
{
"beats": [
13,
14
],
"seconds": 5,
"size": "wide",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "wide shot from inside the dark bedroom looking out the window, the sky outside tinged an unnatural dark red, the courtyard gate banging in the wind, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
15,
16
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [
"P01"
],
"frame": "medium shot of the youth gripping the jade pendant, sitting upright in bed, his expression alert, the dark window behind him, the red sky visible beyond, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in wide framing from inside the bedroom: the sky outside tinged an unnatural dark red, the courtyard gate banging in the wind.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in medium framing: the youth grips the jade pendant, sits upright in bed, his expression alert, the dark window behind him, the red sky visible beyond, the wind growing louder.\n\noverall_soundscape: The courtyard gate banging on its hinges, wind rising to a howl, and the jade pendant emitting an almost inaudible hum.\n\nnon_diegetic_music: A low rumbling tone building in intensity, cutting off abruptly at the segment end."
}
]
},
{
"ep": 2,
"segments": [
{
"id": "E02-01",
"sceneIndex": 1,
"cuts": [
{
"beats": [
1,
3
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth jolting upright in bed, the courtyard gate banging in the background, dogs barking wildly outside the dark window, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
4,
5
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "close-up of the weathered old man at the door, his face pale and trembling, pounding on the wooden door with both hands, panic in his eyes, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
6,
6
],
"seconds": 3,
"size": "medium",
"camera": "Tracking Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth pulling on a robe, moving quickly in the dim bedroom, a tracking shot following him toward the door, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the youth jolts upright in bed, the courtyard gate banging in the background, dogs barking wildly outside the dark window.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in close framing: the old man at the door, his face pale and trembling, pounding on the wooden door, the weathered old man with a shaking, panicked voice (S1) cries: [Chinese] 阿砚！阿砚！ Then: [Chinese] 快起来！出事了！\n[Shot 3] At 00:10.000, the camera cuts to a tracking shot in medium framing: the youth pulls on a robe, moving quickly in the dim bedroom, the tracking shot following him toward the door.\n\noverall_soundscape: Dogs barking frantically, the courtyard gate banging, wooden door being pounded, and rapid footsteps on wooden floorboards.\n\nnon_diegetic_music: N/A"
},
{
"id": "E02-02",
"sceneIndex": 1,
"cuts": [
{
"beats": [
7,
9
],
"seconds": 5,
"size": "wide",
"camera": "Tracking Shot",
"characters": [
"C01"
],
"props": [],
"frame": "wide shot of a dark stone-paved street at night, half the town's people fleeing westward, adults crying, children screaming, a tracking shot following the youth as he pushes through the crowd, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
10,
12
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth in the middle of the fleeing crowd, street lanterns blowing out one by one, his fists clenching, chaos around him, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
13,
15
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C02"
],
"props": [],
"frame": "medium shot of the youth grabbing the old man's arm, the old man pointing toward the street corner unable to speak, the youth looking in that direction, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A tracking shot in wide framing follows the youth as he pushes through the fleeing crowd, half the town's people running westward, adults crying, children screaming, lanterns flickering in the wind.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in medium framing: the youth in the middle of the fleeing crowd, street lanterns blowing out one by one, his fists clenching, chaos swirling around him.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in medium framing: the youth grabs the old man's arm and asks with a worried voice (S1): [Chinese] 爹，怎么了？ The old man points toward the street corner, unable to speak, the youth looking in that direction.\n\noverall_soundscape: Screaming and crying in the night, lanterns whooshing out, wooden shutters banging, and the wind rising.\n\nnon_diegetic_music: N/A"
},
{
"id": "E02-03",
"sceneIndex": 2,
"cuts": [
{
"beats": [
1,
3
],
"seconds": 5,
"size": "wide",
"camera": "Tracking Shot",
"characters": [
"C01",
"C05"
],
"props": [],
"frame": "wide shot of a dark stone-paved street, the youth being pushed forward by the fleeing crowd, a panicked butcher bursting out and grabbing his arm, a tracking shot following the chaos, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
4,
5
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C05"
],
"props": [],
"frame": "close-up of the butcher's face, pale and terrified, his voice cracking as he speaks, his hand gripping the youth's arm, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
6,
6
],
"seconds": 4,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth pulling the butcher's arm, his face urgent, the dark street behind them, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A tracking shot in wide framing follows the chaos: the youth is pushed forward by the fleeing crowd, the panicked butcher bursts out and grabs his arm.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in close framing: the butcher's face pale and terrified, the panicked butcher with a screaming, desperate voice (S1) shouts: [Chinese] 妖怪！妖怪进镇了！ Then releases his grip: [Chinese] 快跑啊！\n[Shot 3] At 00:09.000, the camera cuts to a static shot in medium framing: the youth pulls the butcher's arm, his face urgent, the young man with a sharp, urgent voice (S2) demands: [Chinese] 王叔家的孩子呢？！\n\noverall_soundscape: Screaming and crashing in the dark street, the butcher's panicked footsteps, and the wind howling through the lanternless road.\n\nnon_diegetic_music: N/A"
},
{
"id": "E02-04",
"sceneIndex": 2,
"cuts": [
{
"beats": [
7,
8
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C05"
],
"props": [],
"frame": "close-up of the butcher's trembling face, his voice stuttering with fear, the dark street behind him, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
9,
10
],
"seconds": 5,
"size": "medium",
"camera": "Tracking Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth standing still for a moment, then breaking into a run toward the street corner, a tracking shot following him, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
11,
12
],
"seconds": 4,
"size": "wide",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "wide shot of the youth running toward the street corner, the old man's voice carried by wind, the youth not turning back, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds on the butcher's trembling face: the panicked butcher with a stuttering, terrified voice (S1) says: [Chinese] 孩子？都、都在前面被堵住了！ Then: [Chinese] 那妖怪就在街口！\n[Shot 2] At 00:05.000, the camera cuts to a tracking shot in medium framing: the youth stands still for a moment, then breaks into a run toward the street corner, the tracking shot following him.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in wide framing: the youth running toward the street corner, the old man's voice carried by wind, the youth not turning back.\n\noverall_soundscape: The butcher's panicked footsteps fading, the youth's rapid footsteps on stone, and the wind carrying distant shouts.\n\nnon_diegetic_music: N/A"
},
{
"id": "E02-05",
"sceneIndex": 2,
"cuts": [
{
"beats": [
13,
15
],
"seconds": 5,
"size": "wide",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "wide shot of a street corner, a thick black mist blocking the road, something writhing inside it, a rattling noise coming from within, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
16,
17
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C04"
],
"props": [],
"frame": "medium shot of a dozen villagers collapsed on the ground, a terrified little girl with a topknot crying among them, the youth staring at the scene, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
18,
18
],
"seconds": 3,
"size": "close",
"camera": "Static Shot",
"characters": [
"C04"
],
"props": [],
"frame": "close-up of the little girl's face, her eyes wide with terror, tears streaming, her small hands clutching the ground, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in wide framing holds on the street corner: a thick black mist blocks the road, something writhing inside it, a rattling noise coming from within.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in medium framing: a dozen villagers collapsed on the ground, the terrified little girl with a topknot crying among them, the youth staring at the scene.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in close framing: the little girl's face, her eyes wide with terror, tears streaming, the terrified girl with a high-pitched, frightened voice (S1) cries: [Chinese] 哇——！\n\noverall_soundscape: The writhing and rattling of the black mist, villagers' terrified breathing, and the little girl's crying in the night.\n\nnon_diegetic_music: N/A"
},
{
"id": "E02-06",
"sceneIndex": 2,
"cuts": [
{
"beats": [
19,
20
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C06"
],
"props": [],
"frame": "close-up of a withered scaled hand emerging from the black mist, slowly reaching toward the crying girl, the mist swirling around the hand, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
21,
22
],
"seconds": 5,
"size": "medium",
"camera": "Tracking Shot",
"characters": [
"C01",
"C04"
],
"props": [],
"frame": "medium shot of the youth lunging forward, grabbing the little girl and pulling her into his arms, a tracking shot following him as he turns to run, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
23,
24
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "close-up of the scaled hand sweeping across the youth's back, tearing a strip of fabric from his robe, the youth wincing, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds: a withered scaled hand emerges from the black mist, slowly reaching toward the crying girl, the mist swirling around the hand.\n[Shot 2] At 00:05.000, the camera cuts to a tracking shot in medium framing: the youth lunges forward, grabs the little girl and pulls her into his arms, the tracking shot following him as he turns to run.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in close framing: the scaled hand sweeps across the youth's back, tearing a strip of fabric from his robe, the youth wincing.\n\noverall_soundscape: The wet scraping of the scaled hand, fabric tearing, the youth's sharp intake of breath, and the mist hissing.\n\nnon_diegetic_music: N/A"
},
{
"id": "E02-07",
"sceneIndex": 2,
"cuts": [
{
"beats": [
25,
27
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C04",
"C06"
],
"props": [],
"frame": "medium shot of the youth running with the girl in his arms, the dark shadow creature emerging from the mist behind them, the creature's voice carrying through the night, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
28,
29
],
"seconds": 5,
"size": "wide",
"camera": "Static Shot",
"characters": [
"C06"
],
"props": [],
"frame": "wide shot of a dark shadow lunging out of the black mist, a rush of foul wind, the shadow gaining on the fleeing figures, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
30,
30
],
"seconds": 4,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C04"
],
"props": [],
"frame": "medium shot of the youth still running with the girl, the shadow closing in, no time to dodge, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the youth runs with the girl in his arms, the dark shadow creature emerging from the mist behind them, the creature with a rasping, mocking voice (S1) says: [Chinese] 咯咯咯…… Then: [Chinese] 凡人……也敢抢本座的血食？\n[Shot 2] At 00:05.000, the camera cuts to a static shot in wide framing: a dark shadow lunges out of the black mist, a rush of foul wind, the shadow gaining on the fleeing figures.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in medium framing: the youth still running with the girl, the shadow closing in, no time to dodge.\n\noverall_soundscape: The youth's heavy breathing, the creature's rasping voice echoing, the foul wind rushing past, and the girl's muffled crying.\n\nnon_diegetic_music: N/A"
},
{
"id": "E02-08",
"sceneIndex": 2,
"cuts": [
{
"beats": [
31,
32
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [
"P01"
],
"frame": "close-up of the jade pendant pressed against the youth's chest, glowing with an unbearable heat, the youth's hand clutching it, the pendant burning through his skin, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
33,
34
],
"seconds": 4,
"size": "extreme-close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "extreme close-up of the youth's face, his eyes wide, a scream caught in his throat, the world going black around the edges, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds: the jade pendant pressed against the youth's chest, glowing with an unbearable heat, his hand clutching it, the pendant burning through his skin.\n[Shot 2] At 00:05.000, the camera cuts to an extreme close-up static shot: the youth's face, his eyes wide, the young man with a pained, anguished voice (S1) cries out: [Chinese] 啊！ The world goes black around the edges.\n\noverall_soundscape: The jade pendant humming with an intense heat, a sharp intake of breath, the youth's scream, and then silence as the world goes dark.\n\nnon_diegetic_music: A single high-pitched tone fading into silence."
}
]
},
{
"ep": 3,
"segments": [
{
"id": "E03-01",
"sceneIndex": 1,
"cuts": [
{
"beats": [
1,
3
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C02"
],
"props": [],
"frame": "medium shot of the youth waking up in bed, his chest bandaged, the weathered old man sitting on the edge of the bed looking haggard, morning light through the window, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
4,
5
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "close-up of the old man's face, his voice trembling with relief, morning light on his haggard face, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
6,
6
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "close-up of the youth's face, his voice hoarse, reaching out for the old man, morning light on his pale face, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the youth wakes in bed, chest bandaged, the old man sitting on the edge of the bed looking haggard, morning light through the window.\n[Shot 2] At 00:05.000, the camera cuts to a static shot in close framing: the old man's face, morning light on his haggard features, the weathered old man with a trembling, relieved voice (S1) cries: [Chinese] 阿砚！阿砚你可算醒了！ Then: [Chinese] 你、你吓死爹了……\n[Shot 3] At 00:10.000, the camera cuts to a static shot in close framing: the youth's face, his voice hoarse, the young man with a raspy, concerned voice (S2) asks: [Chinese] 爹……那妖怪……小花……\n\noverall_soundscape: Morning birds chirping outside, the faint creak of the wooden bed, and the old man's shaky breathing.\n\nnon_diegetic_music: N/A"
},
{
"id": "E03-02",
"sceneIndex": 1,
"cuts": [
{
"beats": [
7,
7
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "close-up of the old man wiping his face, his voice steady but strained, morning light on his features, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
8,
8
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "close-up of the old man's face, his eyes glistening, morning light on his weathered features, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
9,
11
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C02",
"C01"
],
"props": [],
"frame": "medium shot of the old man speaking, the youth looking down at his bandaged chest, the morning light between them, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 4.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 8.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds: the old man wipes his face, morning light on his features, the weathered old man with a steady but strained voice (S1) says: [Chinese] 妖怪死了，被人斩了。\n[Shot 2] At 00:04.000, the camera cuts to a static shot in close framing: the old man's eyes glistening, morning light on his weathered features, the same voice (S1) continues: [Chinese] 小花也没事，她爹娘把你背回来的。\n[Shot 3] At 00:08.000, the camera cuts to a static shot in medium framing: the old man speaks, the youth looking down at his bandaged chest, the old man (S1) adds with a heavy heart: [Chinese] 你身上……留了一道疤。\n\noverall_soundscape: Morning birds chirping, the old man's shaky breathing, and the quiet creak of the wooden bed.\n\nnon_diegetic_music: N/A"
},
{
"id": "E03-03",
"sceneIndex": 1,
"cuts": [
{
"beats": [
12,
13
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "close-up of the youth's hand touching the scar on his chest, the scar still red and raw, the bandage pulled aside to reveal the wound, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
14,
15
],
"seconds": 5,
"size": "close",
"camera": "Push In",
"characters": [
"C01"
],
"props": [
"P03"
],
"frame": "close-up of a half-opened plum blossom branch lying on the pillow, the youth's gaze shifting toward it, a slow push in toward the blossom, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
16,
17
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "medium shot of the youth sitting up, the plum blossom in his hand, his gaze drifting toward the direction of the hall, morning light on his face, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds: the youth's hand touches the scar on his chest, the scar still red and raw, the bandage pulled aside to reveal the wound.\n[Shot 2] At 00:05.000, the camera cuts to a close-up with a slow push in: a half-opened plum blossom branch lying on the pillow, the youth's gaze shifting toward it, the push in drawing attention to the blossom.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in medium framing: the youth sits up, the plum blossom in his hand, his gaze drifting toward the direction of the hall, morning light on his face.\n\noverall_soundscape: Morning birds chirping outside, the soft rustle of fabric as the youth sits up, and the faint scent of plum blossoms.\n\nnon_diegetic_music: N/A"
},
{
"id": "E03-04",
"sceneIndex": 1,
"cuts": [
{
"beats": [
18,
18
],
"seconds": 3,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "close-up of the youth's face, his eyes wide with confusion, the plum blossom in his hand, morning light on his features, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
19,
20
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02",
"C01"
],
"props": [
"P03"
],
"frame": "close-up of the old man's face, his voice heavy with a secret, the youth's hand still holding the plum blossom, morning light between them, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
21,
22
],
"seconds": 4,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C02"
],
"props": [],
"frame": "medium shot of the youth looking at the old man, the old man turning his face away, morning light on both of them, the weight of unspoken words, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 3.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 8.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds: the youth's face, his eyes wide with confusion, the plum blossom in his hand, morning light on his features, the young man with a confused, quiet voice (S1) asks: [Chinese] 这、这是哪来的？\n[Shot 2] At 00:03.000, the camera cuts to a static shot in close framing: the old man's face, his voice heavy with a secret, the weathered old man with a low, evasive voice (S2) says: [Chinese] 昨夜……斩妖的那个人留下的。\n[Shot 3] At 00:08.000, the camera cuts to a static shot in medium framing: the youth looks at the old man, the old man turns his face away, morning light on both of them, the weight of unspoken words.\n\noverall_soundscape: Morning birds chirping, the soft rustle of the plum blossom branch, and the quiet between two people.\n\nnon_diegetic_music: N/A"
},
{
"id": "E03-05",
"sceneIndex": 2,
"cuts": [
{
"beats": [
1,
2
],
"seconds": 4,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C01",
"C02"
],
"props": [],
"frame": "medium shot of the old man speaking, the youth listening intently, morning light from the window casting shadows on the wall, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
3,
5
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "medium shot of the old man standing up, walking to the wall, turning around to face the youth, morning light falling on his face, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
6,
6
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "close-up of the old man's face, morning light on his weathered features, his voice grave as he speaks, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 4.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the old man speaks, the youth listens intently, morning light from the window casting shadows on the wall, the weathered old man with a grave, measured voice (S1) says: [Chinese] 他让我带句话给你。 The youth asks: [Chinese] 什么话？\n[Shot 2] At 00:04.000, the camera cuts to a static shot in medium framing: the old man stands up, walks to the wall, turns around to face the youth, morning light falling on his face.\n[Shot 3] At 00:09.000, the camera cuts to a static shot in close framing: the old man's face, morning light on his weathered features, the old man (S1) says with gravity: [Chinese] 他说：此子剑心已醒，凡骨难掩。\n\noverall_soundscape: Morning birds chirping, the old man's footsteps on the wooden floor, and the quiet weight of the words.\n\nnon_diegetic_music: N/A"
},
{
"id": "E03-06",
"sceneIndex": 2,
"cuts": [
{
"beats": [
7,
8
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C02",
"C01"
],
"props": [],
"frame": "close-up of the old man speaking, the youth frozen in shock, morning light on both their faces, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
9,
11
],
"seconds": 5,
"size": "wide",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [],
"frame": "wide shot of the room in morning light, the youth standing frozen, the jade pendant visible in his hand, birds singing outside, morning light on the wall, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
12,
12
],
"seconds": 3,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [
"P01"
],
"frame": "close-up of the jade pendant in the youth's palm, morning light catching its surface, the pendant faintly warm, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds: the old man speaks, the youth frozen in shock, morning light on both their faces, the old man (S1) says with grave finality: [Chinese] 叫他十年后，来玄霄剑宗找我。\n[Shot 2] At 00:05.000, the camera cuts to a static shot in wide framing: the room in morning light, the youth standing frozen, the jade pendant visible in his hand, birds singing outside, morning light on the wall.\n[Shot 3] At 00:10.000, the camera cuts to a static shot in close framing: the jade pendant in the youth's palm, morning light catching its surface, the pendant faintly warm.\n\noverall_soundscape: Morning birds singing, the faint hum of the jade pendant, and the youth's held breath.\n\nnon_diegetic_music: A single sustained cello note at a slow tempo, building softly."
},
{
"id": "E03-07",
"sceneIndex": 2,
"cuts": [
{
"beats": [
13,
14
],
"seconds": 4,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01"
],
"props": [
"P01"
],
"frame": "close-up of the jade pendant in the youth's palm, a faint tremor passing through it, the youth's hand tightening around it, morning light on the jade, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
15,
16
],
"seconds": 5,
"size": "close",
"camera": "Static Shot",
"characters": [
"C01",
"C02"
],
"props": [],
"frame": "close-up of the youth's face turning toward the old man, his eyes searching, the old man looking at him with words unspoken, morning light between them, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
17,
17
],
"seconds": 3,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "medium shot of the old man, his face unreadable, morning light on his weathered features, no words forthcoming, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 4.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in close framing holds: the jade pendant in the youth's palm, a faint tremor passing through it, the youth's hand tightening around it, morning light on the jade.\n[Shot 2] At 00:04.000, the camera cuts to a static shot in close framing: the youth's face turning toward the old man, his eyes searching, the young man with a quiet, pleading voice (S1) asks: [Chinese] 爹，那个仙人……是谁？ The old man looks at him with words unspoken.\n[Shot 3] At 00:09.000, the camera cuts to a static shot in medium framing: the old man, his face unreadable, morning light on his weathered features, no words forthcoming.\n\noverall_soundscape: Morning birds singing, the faint hum of the jade pendant, and the silence between father and son.\n\nnon_diegetic_music: N/A"
},
{
"id": "E03-08",
"sceneIndex": 2,
"cuts": [
{
"beats": [
18,
19
],
"seconds": 5,
"size": "medium",
"camera": "Static Shot",
"characters": [
"C02"
],
"props": [],
"frame": "medium shot of the old man walking to the door, pausing to look back at the youth, morning light on his back, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
20,
21
],
"seconds": 5,
"size": "wide",
"camera": "Tracking Shot",
"characters": [
"C01"
],
"props": [],
"frame": "wide shot of the youth walking to the window, the rooftops of the stone town visible in morning light, a tracking shot following him, cinematic film still, muted earth-tone palette, 16:9"
},
{
"beats": [
22,
23
],
"seconds": 5,
"size": "close",
"camera": "Push In",
"characters": [
"C01"
],
"props": [
"P01"
],
"frame": "close-up of the jade pendant in the youth's palm, a slow push in, the pendant trembling faintly, morning light on the jade, the youth's expression distant, cinematic film still, muted earth-tone palette, 16:9"
}
],
"h3Prompt": "How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the old man walks to the door, pauses to look back at the youth, morning light on his back.\n[Shot 2] At 00:05.000, the camera cuts to a tracking shot in wide framing: the youth walks to the window, the rooftops of the stone town visible in morning light, the tracking shot following him.\n[Shot 3] At 00:10.000, the camera cuts to a close-up with a slow push in: the jade pendant in the youth's palm, the pendant trembling faintly, morning light on the jade, the youth's expression distant.\n\noverall_soundscape: Morning birds singing, the soft creak of the wooden door, and the faint tremor of the jade pendant.\n\nnon_diegetic_music: A single sustained low tone, fading slowly as the pendant trembles.",
"note": "结尾段：玉佩颤动作为悬念钩子，引出后续剧情"
}
]
}
]
}