{ "source": "凡骨问长生", "style": "realistic", "promptLang": "en", "episodes": [ { "ep": 1, "segments": [ { "id": "E01-01", "sceneIndex": 1, "cuts": [ { "beats": [ 1, 1 ], "seconds": 2.5, "size": "extreme-wide", "camera": "Static Shot", "characters": [], "props": [], "frame": "Extreme wide shot, cinematic film still: deep night in an ancient Chinese cultivation-era market town — an empty cobbled street corner under pale moonlight, the old locust tree, low grey-tiled rooftops in thin mist, and a small white cat crouching by the wall as a swirl of black mist rushes toward it.", "h3": "Cinematic, live-action, deep night in an ancient Chinese cultivation-era market town. A static shot holds the extreme wide view of a foggy street corner: pale moonlight, the old locust tree, a small white cat crouching by the wall, and a swirl of black mist rushing toward it." }, { "beats": [ 2, 2 ], "seconds": 2.5, "size": "medium", "camera": "Tracking Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Medium shot, cinematic film still: a lean Han Chinese teenage boy in a patched grey short tunic and straw sandals bursting out of a narrow alley at night, one hand pressed on a cracked jade half-disc pendant that glows faintly warm on a red cord at his chest, a cloth-wrapped wooden practice sword slung across his back, black hair with a few white strands at the temples, ancient Chinese cultivation-era street behind him, motion captured mid-run.", "h3": "the camera cuts to : a tracking shot follows a lean teenage boy in a patched grey tunic and straw sandals bursting out of a narrow alley, one hand pressed on the cracked jade half-disc pendant at his chest that glows faintly warm, a cloth-wrapped wooden practice sword slung across his back." }, { "beats": [ 3, 3 ], "seconds": 2.5, "size": "close", "camera": "Static Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Close-up, cinematic film still: the same lean teenage boy lunging forward to shield a small white cat at the wall corner, black mist bursting apart around them, a white light flaring, the cracked jade half-disc pendant swinging on its red cord, night fog and old town walls behind, patched grey tunic and straw sandals.", "h3": "the camera cuts to : in a static shot close-up, the boy lunges forward to shield the small white cat as the black mist bursts apart and a white light flares, the jade pendant swinging on its red cord." } ], "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 2.50-second mark of the target video; Picture 3 (from Shot 3) aligns with the 5.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, deep night in an ancient Chinese cultivation-era market town. A static shot holds the extreme wide view of a foggy street corner: pale moonlight, the old locust tree, a small white cat crouching by the wall, and a swirl of black mist rushing toward it.\n[Shot 2] At 00:02.500, the camera cuts to : a tracking shot follows a lean teenage boy in a patched grey tunic and straw sandals bursting out of a narrow alley, one hand pressed on the cracked jade half-disc pendant at his chest that glows faintly warm, a cloth-wrapped wooden practice sword slung across his back.\n[Shot 3] At 00:05.000, the camera cuts to : in a static shot close-up, the boy lunges forward to shield the small white cat as the black mist bursts apart and a white light flares, the jade pendant swinging on its red cord.\n\noverall_soundscape: Low night wind through the empty market town, a faint hiss from the black mist, the cat lets out a startled mew, rapid footsteps on cobblestones, and a subtle hum rising from the jade pendant.\n\nnon_diegetic_music: Low, tense string drones with a sparse plucked guqin motif building underneath, cutting off sharply at the white light flare." }, { "id": "E01-02", "sceneIndex": 2, "cuts": [ { "beats": [ 1, 1 ], "seconds": 2.5, "size": "wide", "camera": "Static Shot", "characters": [ "C22" ], "props": [], "frame": "Wide shot, cinematic film still: bright spring daylight in an ancient Chinese cultivation-era market town — an elderly storyteller in a faded grey-blue linen robe with a trimmed grey beard and white-grey hair in a topknot with a wooden hairpin, standing at a worn wooden table under the old locust tree, striking a wooden clapper block with one hand, a brass gavel and a chipped tea bowl on the table, villagers leaning forward in the foreground, warm sun and dust motes.", "h3": "Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. A wide shot frames an elderly storyteller in a faded grey-blue linen robe with a grey beard and white-grey hair in a topknot, striking the wooden clapper block on his worn table under the old locust tree; the camera holds in a static shot while the crowd of villagers leans forward." }, { "beats": [ 2, 2 ], "seconds": 4.5, "size": "medium", "camera": "Push In", "characters": [ "C22" ], "props": [], "frame": "Medium shot, cinematic film still: the elderly storyteller in full voice, one hand raised with the wooden clapper, faded grey-blue linen robe, grey beard, market-town street and locust shade behind him, spring daylight, dust motes in light shafts.", "h3": "the camera cuts to : in a medium shot with a slow push in, the storyteller speaks in a measured, rising storyteller tone: [Chinese] 千年前，剑仙独孤问一人一剑，封了魔渊。 , the brass gavel and chipped tea bowl on the table before him, dust motes drifting in warm light." }, { "beats": [ 3, 3 ], "seconds": 2.5, "size": "close", "camera": "Static Shot", "characters": [ "C22" ], "props": [], "frame": "Close-up, cinematic film still: the elderly storyteller raising a chipped tea bowl to sip, eyes sweeping the crowd with suspense, weathered hands, grey-blue linen sleeve, blurred market-town street in the background, warm spring light.", "h3": "the camera cuts to : a static shot close-up of the storyteller raising the chipped tea bowl to sip, eyes sweeping the audience with suspense." } ], "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 2.50-second mark of the target video; Picture 3 (from Shot 3) aligns with the 7.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. A wide shot frames an elderly storyteller in a faded grey-blue linen robe with a grey beard and white-grey hair in a topknot, striking the wooden clapper block on his worn table under the old locust tree; the camera holds in a static shot while the crowd of villagers leans forward.\n[Shot 2] At 00:02.500, the camera cuts to : in a medium shot with a slow push in, the storyteller speaks in a measured, rising storyteller tone: [Chinese] 千年前，剑仙独孤问一人一剑，封了魔渊。 , the brass gavel and chipped tea bowl on the table before him, dust motes drifting in warm light.\n[Shot 3] At 00:07.000, the camera cuts to : a static shot close-up of the storyteller raising the chipped tea bowl to sip, eyes sweeping the audience with suspense.\n\noverall_soundscape: The sharp crack of the wooden clapper, the murmur of a village crowd, a tea bowl clinking on wood, birds in the locust tree, and warm street ambience.\n\nnon_diegetic_music: Light, lively plucked strings with a storyteller drum pattern, playful and expectant." }, { "id": "E01-03", "sceneIndex": 2, "cuts": [ { "beats": [ 4, 4 ], "seconds": 3.6, "size": "medium", "camera": "Push In", "characters": [ "C22" ], "props": [], "frame": "Medium shot, cinematic film still: the elderly storyteller leaning forward over the worn wooden table, lowering his voice, one hand raised, grey beard and white-grey topknot with wooden hairpin, market-town street behind, spring daylight.", "h3": "Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. In a medium shot with a slow push in, the elderly storyteller leans forward over the worn wooden table, lowers his voice, and says in a hushed, conspiratorial tone: [Chinese] 那日魔渊裂开，黑气冲了三天三夜。 " }, { "beats": [ 5, 5 ], "seconds": 2.5, "size": "wide", "camera": "Static Shot", "characters": [ "C22" ], "props": [], "frame": "Wide shot, cinematic film still: the storyteller stall under the old locust tree — the elderly storyteller slamming the wooden clapper block down on the worn table, villagers leaning back in a gasp, brass gavel and chipped tea bowl on the table, ancient Chinese cultivation-era market town in bright spring daylight.", "h3": "the camera cuts to : a static shot wide view of the storyteller stall as the listeners gasp and the storyteller slams the wooden clapper block down hard on the table." }, { "beats": [ 6, 6 ], "seconds": 4.7, "size": "medium", "camera": "Static Shot", "characters": [ "C22" ], "props": [], "frame": "Medium shot, cinematic film still: the elderly storyteller drawing out his words with a long tone, hands spread over the worn wooden table, faded grey-blue linen robe, market-town street and locust tree behind, warm spring light, dust motes.", "h3": "the camera cuts to : a static shot medium view of the storyteller drawing out the last words in a long, dragging tone: [Chinese] 封渊之后，剑仙再没露过面，有人说是坐化了。 " } ], "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 3.60-second mark of the target video; Picture 3 (from Shot 3) aligns with the 6.10-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. In a medium shot with a slow push in, the elderly storyteller leans forward over the worn wooden table, lowers his voice, and says in a hushed, conspiratorial tone: [Chinese] 那日魔渊裂开，黑气冲了三天三夜。 \n[Shot 2] At 00:03.600, the camera cuts to : a static shot wide view of the storyteller stall as the listeners gasp and the storyteller slams the wooden clapper block down hard on the table.\n[Shot 3] At 00:06.100, the camera cuts to : a static shot medium view of the storyteller drawing out the last words in a long, dragging tone: [Chinese] 封渊之后，剑仙再没露过面，有人说是坐化了。 \n\noverall_soundscape: Gasps from the crowd, the hard crack of the clapper on wood, a few low murmurs, wind in the locust leaves, and the storyteller long pause hanging in the air.\n\nnon_diegetic_music: Sparse dark percussion with a low bamboo flute line, growing heavier toward the end of the shot." }, { "id": "E01-04", "sceneIndex": 2, "cuts": [ { "beats": [ 7, 7 ], "seconds": 2.5, "size": "close", "camera": "Static Shot", "characters": [ "C22" ], "props": [], "frame": "Close-up, cinematic film still: the elderly storyteller pausing mid-sentence, slowly scanning the listeners, deep laugh lines around his eyes, grey beard, wooden clapper held still in his weathered hand, blurred market-town background, spring daylight.", "h3": "Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. A static shot close-up holds the elderly storyteller pausing mid-sentence, slowly scanning the listeners with a knowing look." }, { "beats": [ 8, 8 ], "seconds": 4.5, "size": "medium", "camera": "Static Shot", "characters": [ "C22" ], "props": [], "frame": "Medium shot, cinematic film still: the elderly storyteller miming a pressing gesture with his palm over the worn wooden table, telling the tale of the jade half-disc, grey-blue linen robe, brass gavel and chipped tea bowl in front of him, market town in spring daylight behind.", "h3": "the camera cuts to : a static shot medium view of the storyteller miming a pressing gesture with his palm and saying in a deliberate, emphatic tone: [Chinese] 剑仙把半块玉佩往渊口一按，天地才静下来。 " }, { "beats": [ 9, 9 ], "seconds": 3.8, "size": "close", "camera": "Push In", "characters": [ "C22" ], "props": [], "frame": "Close-up, cinematic film still: the elderly storyteller whispering, eyes narrowed, one finger raised, grey beard and weathered face half in shadow from the locust tree, blurred market-town street behind, spring light.", "h3": "the camera cuts to : in a close-up with a slow push in, the storyteller lowers his voice still further and says: [Chinese] 也有人赌咒，说他还活着，守在渊口。 " } ], "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 2.50-second mark of the target video; Picture 3 (from Shot 3) aligns with the 7.00-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. A static shot close-up holds the elderly storyteller pausing mid-sentence, slowly scanning the listeners with a knowing look.\n[Shot 2] At 00:02.500, the camera cuts to : a static shot medium view of the storyteller miming a pressing gesture with his palm and saying in a deliberate, emphatic tone: [Chinese] 剑仙把半块玉佩往渊口一按，天地才静下来。 \n[Shot 3] At 00:07.000, the camera cuts to : in a close-up with a slow push in, the storyteller lowers his voice still further and says: [Chinese] 也有人赌咒，说他还活着，守在渊口。 \n\noverall_soundscape: The crowd holding its breath, faint wind in the locust tree, the wooden clapper resting on the table, and a distant market-town hum.\n\nnon_diegetic_music: A single plucked guqin note repeating at long intervals, mysterious and open-ended." }, { "id": "E01-05", "sceneIndex": 2, "cuts": [ { "beats": [ 10, 11 ], "seconds": 4.5, "size": "wide", "camera": "Static Shot", "characters": [ "C01" ], "props": [], "frame": "Wide shot, cinematic film still: bright spring daylight in an ancient Chinese cultivation-era market town — a lean teenage boy in a patched grey short tunic and straw sandals carrying a bundle of firewood, stopping at the edge of the storyteller crowd outside a mourning hall with peeling black-lacquered doors and faded white lanterns, a cracked jade half-disc pendant on a red cord at his chest, a cloth-wrapped wooden practice sword on his back.", "h3": "Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. A static shot wide view shows a lean teenage boy in a patched grey tunic carrying a bundle of firewood, stopping at the edge of the storyteller crowd outside the mourning hall gate; he mutters to himself in a low, dry, husky young voice, frowning slightly: [Chinese] 半块玉佩……钥匙？ " }, { "beats": [ 12, 13 ], "seconds": 5, "size": "medium", "camera": "Pan Right", "characters": [ "C01", "C22" ], "props": [], "frame": "Medium shot, cinematic film still: the elderly storyteller at his table glancing toward the edge of the crowd and switching into a comic tale, while the lean teenage boy with the firewood bundle turns and walks in through the peeling black-lacquered mourning hall gate, faded white lanterns above the doorway, spring daylight.", "h3": "the camera cuts to : in a medium shot, a pan right follows the storyteller glance toward the boy as he switches his tale into a comic one, while the boy turns and carries the firewood in through the peeling black-lacquered mourning hall gate." } ], "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 4.50-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, bright spring daylight in an ancient Chinese cultivation-era market town. A static shot wide view shows a lean teenage boy in a patched grey tunic carrying a bundle of firewood, stopping at the edge of the storyteller crowd outside the mourning hall gate; he mutters to himself in a low, dry, husky young voice, frowning slightly: [Chinese] 半块玉佩……钥匙？ \n[Shot 2] At 00:04.500, the camera cuts to : in a medium shot, a pan right follows the storyteller glance toward the boy as he switches his tale into a comic one, while the boy turns and carries the firewood in through the peeling black-lacquered mourning hall gate.\n\noverall_soundscape: The storyteller voice shifting into comic patter, light laughter from the crowd, footsteps on worn cobbles, the creak of the mourning hall gate.\n\nnon_diegetic_music: The previous suspense motif fades; a warmer, everyday guzheng melody takes over." }, { "id": "E01-06", "sceneIndex": 2, "cuts": [ { "beats": [ 14, 15 ], "seconds": 4.9, "size": "wide", "camera": "Static Shot", "characters": [ "C01", "C09" ], "props": [], "frame": "Wide shot, cinematic film still: the courtyard of an ancient Chinese mourning hall in bright spring daylight — an elderly stooped coffin maker in an indigo cotton tunic and hemp apron calling from the yard, a lean teenage boy in a patched grey tunic entering with firewood, then swinging an axe to split a log on a worn chopping block, stacked firewood all around, wood shavings on the ground.", "h3": "Cinematic, live-action, bright spring daylight in the courtyard of an ancient Chinese mourning hall. A static shot wide view shows an elderly stooped coffin maker in an indigo cotton tunic and hemp apron calling in a low, unhurried voice: [Chinese] 阿砚，柴放好，来吃饭。 ; the lean teenage boy in a patched grey tunic enters with firewood, then swings an axe and splits a log cleanly on the worn chopping block." }, { "beats": [ 16, 16 ], "seconds": 2.9, "size": "medium", "camera": "Tilt Down", "characters": [ "C09", "C01" ], "props": [], "frame": "Medium shot, cinematic film still: the elderly stooped coffin maker in an indigo cotton tunic and hemp apron speaking while planing a wooden board, wood shavings curling down, the lean teenage boy listening beside the chopping block, mourning hall courtyard in spring daylight.", "h3": "the camera cuts to : in a medium shot, a tilt down carries from the old coffin maker weathered face to his hands as he planes a wooden board and says in a casual, steady tone: [Chinese] 劈柴要稳，跟做人一个道理。 " }, { "beats": [ 17, 17 ], "seconds": 2.5, "size": "close", "camera": "Static Shot", "characters": [ "C09" ], "props": [], "frame": "Close-up, cinematic film still: weathered hands of the elderly coffin maker gripping a plane against a wooden board, wood shavings curling down, indigo sleeve and worn hemp apron, bright spring light in the mourning hall courtyard.", "h3": "the camera cuts to : a static shot close-up of the plane and the old hands, wood shavings curling down in the spring 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 4.90-second mark of the target video; Picture 3 (from Shot 3) aligns with the 7.80-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, bright spring daylight in the courtyard of an ancient Chinese mourning hall. A static shot wide view shows an elderly stooped coffin maker in an indigo cotton tunic and hemp apron calling in a low, unhurried voice: [Chinese] 阿砚，柴放好，来吃饭。 ; the lean teenage boy in a patched grey tunic enters with firewood, then swings an axe and splits a log cleanly on the worn chopping block.\n[Shot 2] At 00:04.900, the camera cuts to : in a medium shot, a tilt down carries from the old coffin maker weathered face to his hands as he planes a wooden board and says in a casual, steady tone: [Chinese] 劈柴要稳，跟做人一个道理。 \n[Shot 3] At 00:07.800, the camera cuts to : a static shot close-up of the plane and the old hands, wood shavings curling down in the spring light.\n\noverall_soundscape: The axe striking wood with a clean crack, the plane scraping across the board, wood shavings rustling down, a few birds in the courtyard.\n\nnon_diegetic_music: Soft, warm bamboo flute and light percussion, homely and unhurried." }, { "id": "E01-07", "sceneIndex": 2, "cuts": [ { "beats": [ 18, 18 ], "seconds": 2.7, "size": "medium", "camera": "Static Shot", "characters": [ "C09", "C01" ], "props": [], "frame": "Medium shot, cinematic film still: the elderly stooped coffin maker in indigo cotton tunic looking up and speaking to the lean teenage boy in a patched grey tunic, mourning hall courtyard with chopping block and stacked firewood, spring daylight.", "h3": "Cinematic, live-action, bright spring daylight in the courtyard of an ancient Chinese mourning hall. A static shot medium view shows the elderly stooped coffin maker looking up from his work and saying in a plain, matter-of-fact tone: [Chinese] 明日镇上收棺，你帮我抬。 , the lean teenage boy listening beside the chopping block." }, { "beats": [ 19, 19 ], "seconds": 2.5, "size": "extreme-close", "camera": "Push In", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Extreme close-up, cinematic film still: a callused hand of a lean teenage boy touching the cracked jade half-disc pendant with cloud-whorl carving on a faded red cord at his chest, patched grey tunic fabric, warm spring light, ancient Chinese mourning hall courtyard softly blurred behind.", "h3": "the camera cuts to : an extreme close-up with a slow push in on the boy callused hand touching the cracked jade half-disc pendant on the red cord at his chest." }, { "beats": [ 20, 21 ], "seconds": 4.9, "size": "wide", "camera": "Static Shot", "characters": [ "C06", "C01" ], "props": [], "frame": "Wide shot, cinematic film still: mourning hall courtyard in spring daylight — a plump cheerful teenage boy in a coarse undyed hemp tunic with a cloth sash dropping down from the wall, two hot steamed buns steaming in his hands, waving to a lean teenage boy in a patched grey tunic beside the chopping block.", "h3": "the camera cuts to : a static shot wide view as a plump cheerful boy in a coarse hemp tunic drops down from the courtyard wall, two hot steamed buns in his hands, and calls out in a bright, loud voice: [Chinese] 阿砚！趁热，一人一个！ " } ], "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 2.70-second mark of the target video; Picture 3 (from Shot 3) aligns with the 5.20-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, bright spring daylight in the courtyard of an ancient Chinese mourning hall. A static shot medium view shows the elderly stooped coffin maker looking up from his work and saying in a plain, matter-of-fact tone: [Chinese] 明日镇上收棺，你帮我抬。 , the lean teenage boy listening beside the chopping block.\n[Shot 2] At 00:02.700, the camera cuts to : an extreme close-up with a slow push in on the boy callused hand touching the cracked jade half-disc pendant on the red cord at his chest.\n[Shot 3] At 00:05.200, the camera cuts to : a static shot wide view as a plump cheerful boy in a coarse hemp tunic drops down from the courtyard wall, two hot steamed buns in his hands, and calls out in a bright, loud voice: [Chinese] 阿砚！趁热，一人一个！ \n\noverall_soundscape: The old coffin maker low voice, a rustle of cloth as the boy drops from the wall, the soft thud of landing, and the hum of a spring courtyard.\n\nnon_diegetic_music: Warm plucked strings turning playful as the plump boy appears." }, { "id": "E01-08", "sceneIndex": 2, "cuts": [ { "beats": [ 22, 23 ], "seconds": 4.9, "size": "medium", "camera": "Static Shot", "characters": [ "C01", "C06" ], "props": [], "frame": "Medium shot, cinematic film still: a lean teenage boy in a patched grey tunic taking a hot steamed bun and breaking it in half, pushing half back to a plump cheerful boy in a coarse hemp tunic, mourning hall courtyard wall and stacked firewood behind, spring daylight.", "h3": "Cinematic, live-action, bright spring daylight in the courtyard of an ancient Chinese mourning hall. A static shot medium view shows the lean teenage boy in a patched grey tunic taking a hot steamed bun, breaking it in half and pushing half back to the plump boy, saying quietly in a tone that allows no refusal: [Chinese] 你也没吃吧，一人一半。 " }, { "beats": [ 24, 24 ], "seconds": 2.5, "size": "close", "camera": "Static Shot", "characters": [ "C06" ], "props": [], "frame": "Close-up, cinematic film still: a plump cheerful teenage boy wolfing down a steamed bun, cheeks puffed, a smear of flour on his nose, eyes crinkled in a grin, coarse hemp tunic, mourning hall courtyard blurred behind, spring light.", "h3": "the camera cuts to : a static shot close-up of the plump cheerful boy wolfing down the bun, cheeks puffed and grinning." }, { "beats": [ 25, 25 ], "seconds": 2.7, "size": "medium", "camera": "Static Shot", "characters": [ "C06", "C01" ], "props": [], "frame": "Medium shot, cinematic film still: a plump cheerful teenage boy in a coarse hemp tunic patting his chest and promising, a lean teenage boy in a patched grey tunic holding a half bun and listening, courtyard wall behind, spring daylight.", "h3": "the camera cuts to : a static shot medium view of the plump boy patting his chest and promising in a proud, cheerful voice: [Chinese] 明天老地方，我还给你带。 " } ], "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 4.90-second mark of the target video; Picture 3 (from Shot 3) aligns with the 7.40-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, bright spring daylight in the courtyard of an ancient Chinese mourning hall. A static shot medium view shows the lean teenage boy in a patched grey tunic taking a hot steamed bun, breaking it in half and pushing half back to the plump boy, saying quietly in a tone that allows no refusal: [Chinese] 你也没吃吧，一人一半。 \n[Shot 2] At 00:04.900, the camera cuts to : a static shot close-up of the plump cheerful boy wolfing down the bun, cheeks puffed and grinning.\n[Shot 3] At 00:07.400, the camera cuts to : a static shot medium view of the plump boy patting his chest and promising in a proud, cheerful voice: [Chinese] 明天老地方，我还给你带。 \n\noverall_soundscape: The soft sound of biting into a steamed bun, cheerful laughter, and the quiet bustle of a spring courtyard.\n\nnon_diegetic_music: Light, friendly plucked strings with a bouncy rhythm, warm and easy." }, { "id": "E01-09", "sceneIndex": 3, "cuts": [ { "beats": [ 1, 2 ], "seconds": 5, "size": "medium", "camera": "Static Shot", "characters": [ "C01" ], "props": [], "frame": "Medium shot, cinematic film still: deep night in the side room of an ancient Chinese mourning hall — a lean teenage boy in a patched grey tunic crouching before an old chipped wooden cabinet, lifting a loose bottom board, a single oil lamp casting warm lamplight, dark wooden walls.", "h3": "Cinematic, live-action, deep night in the side room of an ancient Chinese mourning hall. A static shot medium view shows a lean teenage boy in a patched grey tunic crouching before an old chipped wooden cabinet, lifting the loose bottom board under the warm glow of a single oil lamp." }, { "beats": [ 3, 3 ], "seconds": 2.5, "size": "extreme-close", "camera": "Push In", "characters": [], "props": [ "P04" ], "frame": "Extreme close-up, cinematic film still: a washed-white cotton handkerchief with a faded red plum-blossom branch embroidered in one corner and a line of small embroidered characters, lying flat on worn wooden floorboards in warm oil-lamplight, deep night in an ancient Chinese mourning hall side room.", "h3": "the camera cuts to : an extreme close-up with a slow push in on the washed-white handkerchief with faded red plum-blossom embroidery and a line of small embroidered characters, lying in the lamplight." }, { "beats": [ 4, 4 ], "seconds": 2.7, "size": "close", "camera": "Static Shot", "characters": [ "C01" ], "props": [], "frame": "Close-up, cinematic film still: the face of a lean teenage boy lit by a single oil lamp, eyes tracing the embroidered characters on a handkerchief held below frame, lips pressed together, black hair with white strands at the temples, dark wooden mourning hall side room at night.", "h3": "the camera cuts to : a static shot close-up of the boy face in the lamplight, eyes tracing the embroidered characters, lips pressed; he says in an off-screen voiceover, his inner voice strained and tight: [Chinese] 娘的东西，怎么在爹这儿。 , while his lips remain completely closed." } ], "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 7.50-second mark of the target video.\n\nintegrated_multimodal_description:\n[Shot 1] Cinematic, live-action, deep night in the side room of an ancient Chinese mourning hall. A static shot medium view shows a lean teenage boy in a patched grey tunic crouching before an old chipped wooden cabinet, lifting the loose bottom board under the warm glow of a single oil lamp.\n[Shot 2] At 00:05.000, the camera cuts to : an extreme close-up with a slow push in on the washed-white handkerchief with faded red plum-blossom embroidery and a line of small embroidered characters, lying in the lamplight.\n[Shot 3] At 00:07.500, the camera cuts to : a static shot close-up of the boy face in the lamplight, eyes tracing the embroidered characters, lips pressed; he says in an off-screen voiceover, his inner voice strained and tight: [Chinese] 娘的东西，怎么在爹这儿。 , while his lips remain completely closed.\n\noverall_soundscape: The faint crackle of the oil lamp, the scrape of the cabinet board, cloth rustling, and the boy slow, quiet breathing.\n\nnon_diegetic_music: A lone, low cello note with a soft pulse, intimate and uneasy." }, { "id": "E01-10", "sceneIndex": 3, "cuts": [ { "beats": [ 5, 6 ], "seconds": 5, "size": "wide", "camera": "Static Shot", "characters": [ "C01", "C09" ], "props": [], "frame": "Wide shot, cinematic film still: deep night in an ancient Chinese mourning hall courtyard — an elderly stooped coffin maker in an indigo cotton tunic straightening as he stops stacking firewood, while through the lit window of the side room a lean teenage boy hastily tucks something into an old cabinet and closes the door, moonlight and thin mist.", "h3": "Cinematic, live-action, deep night in the courtyard of an ancient Chinese mourning hall. A static shot wide view shows the elderly stooped coffin maker in an indigo cotton tunic straightening as he stops stacking firewood, while through the lit window of the side room the lean teenage boy hastily tucks the handkerchief back under the cabinet board and closes the door." }, { "beats": [ 7, 8 ], "seconds": 2.9, "size": "medium", "camera": "Static Shot", "characters": [ "C09", "C01" ], "props": [], "frame": "Medium shot, cinematic film still: the gaunt silhouette of an elderly coffin maker in an indigo cotton tunic standing in the side-room doorway at night, speaking to a lean teenage boy in a patched grey tunic whose back is straight beside the old cabinet, oil lamp glow, dark wooden room.", "h3": "the camera cuts to : a static shot medium view through the side-room doorway — the old coffin maker gaunt silhouette asks in a hoarse voice: [Chinese] 还没睡？ ; the boy answers in a steady, ordinary tone, his back straight: [Chinese] 就睡。爹也早点歇。 " } ], "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, deep night in the courtyard of an ancient Chinese mourning hall. A static shot wide view shows the elderly stooped coffin maker in an indigo cotton tunic straightening as he stops stacking firewood, while through the lit window of the side room the lean teenage boy hastily tucks the handkerchief back under the cabinet board and closes the door.\n[Shot 2] At 00:05.000, the camera cuts to : a static shot medium view through the side-room doorway — the old coffin maker gaunt silhouette asks in a hoarse voice: [Chinese] 还没睡？ ; the boy answers in a steady, ordinary tone, his back straight: [Chinese] 就睡。爹也早点歇。 \n\noverall_soundscape: Night crickets, the creak of the cabinet door, the old coffin maker hoarse voice through the doorway, and the rustle of the boy clothes.\n\nnon_diegetic_music: Sparse, quiet strings holding a single low pedal note, wary and restrained." }, { "id": "E01-11", "sceneIndex": 3, "cuts": [ { "beats": [ 9, 10 ], "seconds": 5, "size": "wide", "camera": "Static Shot", "characters": [ "C09" ], "props": [], "frame": "Wide shot, cinematic film still: deep night in an ancient Chinese market town — an elderly stooped coffin maker in indigo cotton tunic turning and walking back into the mourning hall, while beyond the peeling black-lacquered gate black mist surges along the street corner toward a small white cat crouching by the wall, pale moonlight and thin fog.", "h3": "Cinematic, live-action, deep night in an ancient Chinese market town. A static shot wide view shows the elderly stooped coffin maker nodding and turning back into the mourning hall; beyond the peeling black-lacquered gate, black mist surges along the street corner toward a small white cat crouching by the wall." }, { "beats": [ 11, 12 ], "seconds": 3.2, "size": "medium", "camera": "Tracking Shot", "characters": [ "C01" ], "props": [ "P01" ], "frame": "Medium shot, cinematic film still: a lean teenage boy in a patched grey tunic shouting and springing up from beside an old cabinet, clutching the cracked jade half-disc pendant flaring hot at his chest, then dashing out the door of the mourning hall into the night street, motion captured mid-run, red cord and jade swinging.", "h3": "the camera cuts to : a tracking shot follows the lean teenage boy as he shouts in a sharp, rising voice: [Chinese] 小花！ , springs up, clutches the jade half-disc pendant flaring hot at his chest, and dashes out the door into the night street." } ], "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, deep night in an ancient Chinese market town. A static shot wide view shows the elderly stooped coffin maker nodding and turning back into the mourning hall; beyond the peeling black-lacquered gate, black mist surges along the street corner toward a small white cat crouching by the wall.\n[Shot 2] At 00:05.000, the camera cuts to : a tracking shot follows the lean teenage boy as he shouts in a sharp, rising voice: [Chinese] 小花！ , springs up, clutches the jade half-disc pendant flaring hot at his chest, and dashes out the door into the night street.\n\noverall_soundscape: The creak of the mourning hall door, rising wind, the cat frightened cry, urgent footsteps, and the jade pendant low hum building.\n\nnon_diegetic_music: Tense drums and low strings accelerating, cutting out as the boy bursts into the night." } ] } ] }