迷你城市｜一天采购 vlog

提示词原文（一字未改）

[SPEC] 12 秒，9:16 竖屏，24fps，720×1280，超写实真人城市生活 vlog，恰好 6 段相连场景、每段约 2 秒，手持 vlog 摄影，无文字叠层。

[CHARACTER LOCK] 一名明确成年的 26 岁东亚女性，东亚骨相特征清晰：柔和鹅蛋脸、深棕色杏仁眼带浅双眼皮、鼻梁细直、唇形自然，妆容为精致日常妆。齐肩黑色直发，一侧别在耳后，鬓角留几缕碎发。米白色宽松衬衫、浅蓝直筒牛仔裤、白色低帮运动鞋，单肩挎一只小号帆布购物袋。6 段场景里保持同一张脸、同一发型、同一服装、同一体型比例与同一只购物袋。

[SETTING & LIGHT] 白天的中国现代沿海城市。自然光充足、色调干净略低饱和，橱窗有真实反射，特写镜头浅景深。所有店铺招牌留白或不可辨认，画面中不出现任何品牌名。

[SHOT LIST]
0–2 秒：明亮的小公寓室内。她在玄关镜前整理一下，从木桌上拿起手机、钥匙和折好的帆布袋，开门出门；自然手持 vlog 构图，窗外日光洒进来。
2–4 秒：热闹的街市。背后跟拍她走过水果摊、蔬菜摊与小店橱窗；行人与一辆驶过的电动车自然移动；插入一小段她边走边笑的自拍式正面镜头。
4–6 秒：蔬菜摊特写。她的手挑起番茄、黄瓜、青菜与柠檬，端详后放进帆布袋；摊主的手递回零钱；背景是虚化的成筐鲜亮蔬菜。
6–8 秒：社区小超市货架。俯拍她的手把纸包面包、玻璃瓶和几件颜色鲜亮但无品牌的零食放进购物篮；她又看见一件，停顿一下，带着一点好笑多拿了一件。
8–10 秒：回到繁忙街道，双手拎着两只装满的购物袋。先是一小段穿过人群的 POV 镜头，再切到她略显疲惫又觉得好笑的自拍式镜头；车流与过街行人在身后移动；她走到公寓楼门口。
10–12 秒：厨房里，她把袋子放上台面；俯拍蔬菜、面包与水果铺开的全景。她呼一口气，随手把头发松松扎起，掰一小块面包咬下，露出满足的笑。收在温暖的俯拍构图上。

[TEXTURE] 真实手持微抖、自然眨眼、衣物与袋子随动作摆动，拎起满袋时有可信的重量感。各段之间皮肤质感与头发长度一致。不用变速、不用变形转场。

[SOUND] 连续环境声：门响、脚步、街边人声、自行车铃、市场叫卖、购物袋摩擦、厨房声响。不加音乐重音、不加旁白。

[NEGATIVE PROMPT] 换脸、五官漂移、网红模板脸、欧美骨相、非东亚面孔、未成年观感、场景之间服装或发长变化、多出的肢体、多指、手部畸形、物体悬空、可读文字、品牌名、Logo、字幕、水印、背景静止、画面闪烁、过曝。

英文含义说明

[SPEC] 12 seconds, 9:16 vertical, 24fps, 720x1280, ultra-photoreal live-action city lifestyle vlog, exactly 6 connected scenes of about 2 seconds each, handheld vlog camera, no text overlays.

[CHARACTER LOCK] A clearly adult 26-year-old East Asian woman with distinctly East Asian features: soft oval face, dark-brown almond eyes with subtle double eyelids, a refined straight nose bridge, naturally shaped lips, and polished everyday makeup. Shoulder-length straight black hair tucked behind one ear, a few loose strands at the temple. She wears a cream oversized shirt, straight-leg light-blue jeans, white low-top sneakers and a small canvas tote bag over one shoulder. Keep exactly the same face, hairstyle, outfit, body proportions and tote bag in all six scenes.

[SETTING & LIGHT] A modern Chinese coastal city in bright daytime. Warm natural daylight, clean slightly desaturated street color, real reflections on shop windows, shallow depth of field on close-ups. All storefront signs are blank or unreadable; no brand names anywhere.

[SHOT LIST]
0-2s: inside her small bright apartment. She checks her reflection in a hallway mirror, picks up phone, keys and the folded tote from a wooden table, opens the door and steps out; natural handheld vlog framing, daylight through the window.
2-4s: a lively street market. Tracking shot from behind as she walks past fruit carts, vegetable stalls and shop displays; pedestrians and a passing scooter move naturally; brief selfie-style front shot of her smiling as she walks.
4-6s: vegetable stall close-ups. Her hands pick up tomatoes, cucumbers, leafy greens and lemons, check them and place them into the tote; a vendor's hands hand back change; colorful produce in shallow-focus baskets behind.
6-8s: a small neighborhood grocery aisle. Overhead shot of her hands placing a paper-wrapped loaf, a glass bottle and a few brightly wrapped but unbranded snacks into a basket; she notices one more, pauses and adds it with a small amused smile.
8-10s: back on the busy street, now carrying two full grocery bags. A short POV shot through the crowd, then a selfie-style shot of her looking mildly tired but amused; traffic and crossing pedestrians move behind her; she reaches her apartment building entrance.
10-12s: in her kitchen, she sets the bags on the counter; a top-down shot of vegetables, bread and fruit spread out. She exhales, ties her hair back loosely, breaks off a piece of bread and takes a bite, then relaxes into a satisfied smile. End on the warm overhead composition.

[TEXTURE] Real handheld micro-shake, natural blinks, fabric and bag movement, believable weight when she lifts the full bags. Consistent skin texture and hair length across cuts. No speed ramps, no morph transitions.

[SOUND] Continuous natural ambience: door click, footsteps, street chatter, bicycle bell, market voices, rustling bags, kitchen sounds. No music stingers, no narration.

[NEGATIVE PROMPT] face swap, drifting features, influencer-template face, Western/Caucasian bone structure, non-Asian face, underage or teenage look, changing outfit or hair length between scenes, extra limbs, extra fingers, deformed hands, floating objects, readable text, brand names, logos, subtitles, watermark, frozen background, flicker, overexposure.