[ { "id": "E01-03", "sceneIndex": 2, "cuts": [ { "beats": [ 5, 5 ], "seconds": 3, "size": "medium", "camera": "Static Shot", "characters": [ "C01", "C09", "C06", "C22" ], "props": [ "P01" ], "frame": "A medium shot frames the whole teahouse audience in a spring-lit hall, showing listeners inhale sharply while the old storyteller slams the wake-up block onto the table." }, { "beats": [ 6, 6 ], "seconds": 5, "size": "close", "camera": "Static Shot", "characters": [ "C22" ], "props": [ "P01" ], "frame": "A close shot isolates the aged storyteller in his patched robe as he lifts the chipped tea bowl and speaks of the sealed mountain and absent sword immortal in a hushed tone." }, { "beats": [ 7, 7 ], "seconds": 3, "size": "wide", "camera": "Pan Left", "characters": [ "C01", "C09", "C06", "C22" ], "props": [ "P01" ], "frame": "A wide shot with a slow pan left follows the old storyteller's deliberate pause and sweeping gaze across the gray-clad youth, the silent coffin maker, and the stout boy in the spring-lit teahouse." } ], "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.\nintegrated_multimodal_description:\n[Shot 1] [object Object]\n[Shot 2] At 3.000, the camera cuts to : [object Object]\n[Shot 3] At 8.000, the camera cuts to : [object Object]\noverall_soundscape: The sharp crack of the wake-up block hitting the table, a collective sharp intake of breath, the soft clink of the chipped tea bowl, and faint spring birdsong and wind through the teahouse.\nnon_diegetic_music: A sparse, low woodwind-and-guzheng theme that darkens under the hushed line, then thins to near silence during the sweeping gaze." }, { "id": "E01-06", "sceneIndex": 2, "cuts": [ { "beats": [ 17, 17 ], "seconds": 3, "size": "wide", "camera": "Static Shot", "characters": [ "C01", "C09" ], "props": [ "P01" ], "frame": "Wide shot, a middle-aged coffin maker in plain clothes silently planes a wooden board while wood shavings scatter to the ground, a sixteen-year-old gray-clad youth watching nearby." }, { "beats": [ 18, 18 ], "seconds": 3, "size": "medium", "camera": "Static Shot", "characters": [ "C09", "C01" ], "props": [ "P01" ], "frame": "Medium shot, the middle-aged coffin maker in rough cloth speaks as he works, asking the sixteen-year-old gray-clad youth to help carry a coffin in town tomorrow, the youth listening." }, { "beats": [ 19, 20 ], "seconds": 4, "size": "close", "camera": "Tracking Shot", "characters": [ "C01", "C06" ], "props": [ "P01" ], "frame": "Close shot, the sixteen-year-old gray-clad youth nods and touches the half jade pendant at his chest, then a round-faced chubby youth in hemp clothing drops over the wall holding two hot steamed buns, waving." }, { "beats": [ 21, 21 ], "seconds": 3, "size": "medium", "camera": "Static Shot", "characters": [ "C06", "C01" ], "props": [ "P01" ], "frame": "Medium shot, the round-faced chubby youth in short hemp garments raises warm steamed buns, calling out for the gray-clad youth to take one each while they are still hot, a half jade pendant visible." } ], "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 6.00-second mark of the target video; Picture 4 (from Shot 4) aligns with the 10.00-second mark of the target video.\nintegrated_multimodal_description:\n[Shot 1] Wide shot holds as the middle-aged coffin maker planes a board, wood shavings cascading to the ground while the gray-clad youth watches nearby.\n[Shot 2] At 3.000, the camera cuts to : Medium shot follows the middle-aged coffin maker (S1), still working, saying, 明日镇上收棺，你帮我抬。 the gray-clad youth listening.\n[Shot 3] At 6.000, the camera cuts to : Close shot captures the gray-clad youth nodding and touching the half jade pendant at his chest before a round-faced chubby youth in hemp clothing drops over the wall, waving two hot steamed buns.\n[Shot 4] At 10.000, the camera cuts to : Medium shot tracks the round-faced chubby youth (S2) raising the warm buns and calling, 阿砚！趁热，一人一个！ the gray-clad youth's half jade pendant visible.\noverall_soundscape: Planing wood and falling shavings; light thud as the chubby youth lands over the wall, muffled warmth from the steaming buns.\nnon_diegetic_music: Gentle plucked strings with a light folk pulse, warm and unhurried." }, { "id": "E01-09", "sceneIndex": 3, "cuts": [ { "beats": [ 5, 6 ], "seconds": 4, "size": "extreme-wide", "camera": "Static Shot", "characters": [ "C01", "C09" ], "props": [ "P01", "P04" ], "frame": "Extreme-wide night-fog yard shot: the middle-aged coffin maker pauses among stacked firewood while the gray-clad sixteen-year-old boy hides a cloth into the cabinet." }, { "beats": [ 7, 8 ], "seconds": 3, "size": "medium", "camera": "Static Shot", "characters": [ "C01", "C09" ], "props": [ "P01", "P04" ], "frame": "Medium night-fog yard shot: the middle-aged coffin maker asks quietly if the boy is still awake, and the gray-clad sixteen-year-old boy answers he will sleep soon and tells his father to rest." }, { "beats": [ 9, 9 ], "seconds": 3, "size": "wide", "camera": "Tracking Shot", "characters": [ "C09" ], "props": [ "P01" ], "frame": "Wide night-fog tracking shot: the silent middle-aged coffin maker hums in acknowledgment, turns away from the stacked firewood, and walks back into the house." } ], "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 7.00-second mark of the target video.\nintegrated_multimodal_description:\n[Shot 1] Extreme-wide night-fog yard shot continues: the gray-clad boy shoves the cloth beneath the cabinet and closes the door as the middle-aged coffin maker pauses, back turned to the stacked firewood.\n[Shot 2] At 4.000, the camera cuts to : Medium night-fog yard shot holds: the middle-aged coffin maker (S1) asks in a low voice \"[Chinese]还没睡？\", and the gray-clad boy (S2) answers \"[Chinese]就睡。爹也早点歇。\".\n[Shot 3] At 7.000, the camera cuts to : Wide night-fog tracking shot follows: the silent middle-aged coffin maker (S1) hums in acknowledgment, turns from the firewood, and walks back into the house while the camera keeps pace.\noverall_soundscape: Thin mist muffles the rustle of dry firewood and the soft creak of the cabinet door; a faint lantern flame flickers in the deep-night silence.\nnon_diegetic_music: Sparse, low wooden-string motif under distant night air, nearly hushed, holding the uneasy calm." }, { "id": "E01-10", "sceneIndex": 3, "cuts": [ { "beats": [ 10, 11 ], "seconds": 3, "size": "wide", "camera": "Push In", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Wide night-street shot under foggy glow as black mist surges from the corner, a lone gray-robed teenage figure crouching near the wall recoils." }, { "beats": [ 12, 12 ], "seconds": 3, "size": "close", "camera": "Static Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Close shot of the gray-clad youth springing upright, clutching the scorching jade pendant as he rushes out of the doorway into the murk." } ], "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.\nintegrated_multimodal_description:\n[Shot 1] A static wide shot under foggy moonlight as black mist bursts from the corner and rolls toward the wall; the gray-clad youth recoils and shouts (S1): [Chinese]小花！\n[Shot 2] At 3.000, the camera cuts to : A close shot of the gray-clad youth springing upright, flinching as the jade pendant scorches his chest, then a quick tracking push follows him dashing out of the doorway into the murk.\noverall_soundscape: Night wind stirs the thin mist; black mist rolls over wet cobbles with a low hiss. A sharp intake of breath, a gasp at the searing jade, and rapid footsteps rush into the dark.\nnon_diegetic_music: Low, tense strings and a lone drumbeat swell as the mist strikes, then cut off as the youth bolts into the murk." }, { "id": "E01-05", "sceneIndex": 2, "cuts": [ { "beats": [ 11, 11 ], "seconds": 2, "size": "extreme-close", "camera": "Static Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Extreme close-up of the broken jade pendant dangling on a thread, pale spring light glinting across its fractured edge as a grey-clad sixteen-year-old youth fingers the shard, eyes narrowing in a silent questioning glance." }, { "beats": [ 12, 12 ], "seconds": 3, "size": "medium", "camera": "Tracking Shot", "characters": [ "C22", "C01" ], "props": [ "P01" ], "frame": "Medium tracking shot following the old storyteller in a worn robe as he spots the grey-clad youth among the crowd, snaps shut his wooden block, then shifts tone to tell a comic tale, teacup with a chipped rim resting near his hand." }, { "beats": [ 13, 14 ], "seconds": 4, "size": "wide", "camera": "Static Shot", "characters": [ "C09", "C01" ], "props": [], "frame": "Wide shot of a silent middle-aged coffin maker in coarse cloth standing by a courtyard gate while the grey-clad sixteen-year-old youth hoists bundled firewood through the doorway, answering with a single nod before the wood settles down." }, { "beats": [ 15, 15 ], "seconds": 3, "size": "medium", "camera": "Static Shot", "characters": [ "C09", "C01" ], "props": [], "frame": "Medium shot as the grey-clad youth answers with a grunt, swinging an axe overhead and splitting a log cleanly in two, splinters flying under bright spring sun while the coarse-clad coffin maker watches without speaking." }, { "beats": [ 16, 16 ], "seconds": 3, "size": "close", "camera": "Static Shot", "characters": [ "C09", "C01" ], "props": [], "frame": "Close shot of the middle-aged coffin maker speaking calmly to the grey-clad youth, gesturing toward the split wood, his tone firm as he compares steady axe strokes to steady living under the warm white daylight of early spring." } ], "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 2.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 5.00-second mark of the target video; Picture 4 (from Shot 4) aligns with the 9.00-second mark of the target video; Picture 5 (from Shot 5) aligns with the 12.00-second mark of the target video.\nintegrated_multimodal_description:\n[Shot 1] [object Object]\n[Shot 2] At 2.000, the camera cuts to : [object Object]\n[Shot 3] At 5.000, the camera cuts to : [object Object]\n[Shot 4] At 9.000, the camera cuts to : [object Object]\n[Shot 5] At 12.000, the camera cuts to : [object Object]\noverall_soundscape: A faint chime of broken jade, the storyteller's wooden block snapping shut, the hush of settling firewood, a sharp crack as the log splits, splinters pattering on the courtyard stone.\nnon_diegetic_music: N/A" }, { "id": "E01-07", "sceneIndex": 2, "cuts": [ { "beats": [ 22, 23 ], "seconds": 4, "size": "medium", "camera": "Push In", "characters": [ "C01", "C06" ], "props": [ "P01" ], "frame": "A medium push-in shot: a sixteen-year-old grey-robed youth with a jade pendant tears a steamed bun in half and presses one piece back into the hands of the round-faced lad in coarse hemp tunic." }, { "beats": [ 24, 24 ], "seconds": 3, "size": "close", "camera": "Static Shot", "characters": [ "C06" ], "props": [], "frame": "A close static shot of the round-faced lad in coarse hemp tunic beaming wide as he gulps down the half-bun in two quick bites and swallows happily." }, { "beats": [ 25, 25 ], "seconds": 3, "size": "wide", "camera": "Tracking Shot", "characters": [ "C01", "C06" ], "props": [], "frame": "A wide tracking shot follows the round-faced lad as he promises to bring another bun to the same place tomorrow, while the grey-robed youth listens and nods." } ], "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 7.00-second mark of the target video.\nintegrated_multimodal_description:\n[Shot 1] [object Object]\n[Shot 2] At 4.000, the camera cuts to : [object Object]\n[Shot 3] At 7.000, the camera cuts to : [object Object]\noverall_soundscape: Soft crunch of steamed bread tearing, quick chewing and a pleased swallow, light spring breeze through leaves, and faint distant street chatter among the drifting dust motes.\nnon_diegetic_music: A gentle, warm woodwind-and-guzheng melody that stays airy and understated." }, { "id": "E01-01", "sceneIndex": 1, "cuts": [ { "beats": [ 1, 1 ], "seconds": 3, "size": "wide", "camera": "Static Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "A wide shot of a foggy night street where a dark mist surges from the intersection and rushes toward a small cat crouching by the corner wall, the ominous haze filling the frame with eerie motion." }, { "beats": [ 2, 2 ], "seconds": 3, "size": "medium", "camera": "Push In", "characters": [ "C01" ], "props": [ "P01" ], "frame": "A medium shot pushes in on the gray-robed teen bursting from the alleyway, one hand pressed over the half jade pendant glowing warm against his chest, his face tense and urgent in the dim lamplight." }, { "beats": [ 3, 3 ], "seconds": 3, "size": "extreme-wide", "camera": "Tracking Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "An extreme-wide tracking shot follows the gray-robed teen lunging before the small cat as the black mist abruptly scatters and a blinding white flash erupts, swallowing the night street in a sudden burst of light." } ], "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 6.00-second mark of the target video.\nintegrated_multimodal_description:\n[Shot 1] [object Object]\n[Shot 2] At 3.000, the camera cuts to : [object Object]\n[Shot 3] At 6.000, the camera cuts to : [object Object]\noverall_soundscape: Deep night quiet broken by a low wind as the mist surges; rapid footsteps and a muffled heartbeat-pulse, then a sharp airy boom when the white flash erupts.\nnon_diegetic_music: Tense low drone with swelling strings that cut abruptly on the flash." }, { "id": "E01-02", "sceneIndex": 2, "cuts": [ { "beats": [ 1, 1 ], "seconds": 3, "size": "wide", "camera": "Static Shot", "characters": [ "C01", "C09", "C06", "C22" ], "props": [ "P01" ], "frame": "A wide shot of the old storyteller raising his wooden block while listeners in the teahouse lean forward as one." }, { "beats": [ 2, 2 ], "seconds": 5, "size": "close", "camera": "Push In", "characters": [ "C22" ], "props": [ "P01" ], "frame": "A close shot slowly pushes toward the old storyteller as he speaks of the sword immortal sealing the demon abyss." }, { "beats": [ 3, 3 ], "seconds": 3, "size": "close", "camera": "Static Shot", "characters": [ "C22" ], "props": [ "P01" ], "frame": "A close shot holds on the old storyteller lifting a chipped tea bowl to his lips, keeping the crowd's suspense." }, { "beats": [ 4, 4 ], "seconds": 4, "size": "medium", "camera": "Arc Shot", "characters": [ "C22" ], "props": [ "P01" ], "frame": "A medium shot frames the old storyteller describing the abyss splitting and black qi surging for three days." } ], "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 11.00-second mark of the target video.\nintegrated_multimodal_description:\n[Shot 1] [object Object]\n[Shot 2] At 3.000, the camera cuts to : [object Object]\n[Shot 3] At 8.000, the camera cuts to : [object Object]\n[Shot 4] At 11.000, the camera cuts to : [object Object]\noverall_soundscape: Soft teahouse murmur, wooden block clap, the old storyteller's voice, a tea bowl's faint clink, and spring breeze through the courtyard.\nnon_diegetic_music: Warm, sparse guqin and bamboo flute lines, building gently with each tale beat." }, { "id": "E01-04", "sceneIndex": 2, "cuts": [ { "beats": [ 8, 8 ], "seconds": 5, "size": "extreme-wide", "camera": "Static Shot", "characters": [ "C22" ], "props": [ "P01" ], "frame": "Extreme wide shot of a crowd by a chasm as an old storyteller presses a jade token onto the edge and silence settles over spring daylight." }, { "beats": [ 9, 9 ], "seconds": 4, "size": "close", "camera": "Push In", "characters": [ "C22" ], "props": [ "P01" ], "frame": "Close shot of an old storyteller with a worn tea bowl as he vows that someone still lives and keeps watch at the chasm mouth." }, { "beats": [ 10, 10 ], "seconds": 3, "size": "wide", "camera": "Tracking Shot", "characters": [ "C01" ], "props": [], "frame": "Wide shot outside the crowd as a gray-clad young man carrying firewood pauses mid-step in the bright spring sunshine." } ], "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.\nintegrated_multimodal_description:\n[Shot 1] [object Object]\n[Shot 2] At 5.000, the camera cuts to : [object Object]\n[Shot 3] At 9.000, the camera cuts to : [object Object]\noverall_soundscape: Spring wind through leaves, muffled crowd murmur, the dull clink of the jade token meeting stone, the creak of a tea bowl setting down, and the soft rustle of a firewood bundle shifting as footsteps stop.\nnon_diegetic_music: A sparse, low dizi melody that hushes at the jade touch, then thins to a lone, distant note as the gray-clad youth pauses." }, { "id": "E01-08", "sceneIndex": 3, "cuts": [ { "beats": [ 1, 1 ], "seconds": 3, "size": "medium", "camera": "Static Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "A night-fog medium view of the mortuary side room, one oil lamp burning low while the gray-clad teen crouches by an old wooden cabinet." }, { "beats": [ 2, 3 ], "seconds": 4, "size": "close", "camera": "Push In", "characters": [ "C01" ], "props": [ "P01", "P04" ], "frame": "Close push-in on the false bottom panel, the teen's hands drawing out a neatly folded plum-blossom handkerchief from the cabinet's hidden floor." }, { "beats": [ 4, 4 ], "seconds": 3, "size": "close", "camera": "POV", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Close POV of tiny embroidered characters on the kerchief corner beneath the lamp glow, the gray-clad teen reading each word slowly." } ], "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 7.00-second mark of the target video.\nintegrated_multimodal_description:\n[Shot 1] [object Object]\n[Shot 2] At 3.000, the camera cuts to : [object Object]\n[Shot 3] At 7.000, the camera cuts to : [object Object]\noverall_soundscape: Thin night wind threads through the fog; the false panel creaks, cloth rustles softly, and the oil lamp gives a faint crackle.\nnon_diegetic_music: A sparse, lonely guqin phrase with a barely audible pulse, holding silence under the off-screen line." } ]