OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

明亮商场中庭的成年女性购物自拍

Adult woman taking a shopping selfie in a bright mall atrium

一张9:16手机前置镜头风格的商场生活方式自拍,明确成年的原创女性穿得体的白色衬衫和米色上衣,右手持手机、左手提黄绿色购物袋,背景是明亮现代的豪华商场中庭。

明亮商场中庭的成年女性购物自拍 — AI image creation
明亮商场中庭的成年女性购物自拍

提示词 / Prompt

中文提示词

9:16竖屏手机前置镜头风格的生活方式自拍,一位明确成年的原创东亚女性使用人物参考 ref-10a-v1,拥有心形脸、自然肤色、深栗色长发和柔和法式刘海,一侧头发自然别在耳后露出银色耳钉,表情亲切自信,闭嘴微笑,头部向右轻倾。她穿不透明的白色长袖纽扣衬衫,整齐扣合并自然垂落在米色圆领内搭外,服装得体,不出现胸部聚焦、透明材质、内衣式设计或品牌标志;佩戴银蓝色简洁项链和蓝色珠子手链。她向前轻轻倾身自拍,右手自然握手机,左手握住黄绿色购物袋手柄,双手清晰可见,每只手五个手指,手部解剖正确而放松。前景左下方出现购物袋与手链细节,中景展示白色衬衫、米色内搭和项链,背景是明亮现代的商场中庭,高大白色柱子、抛光地面、大窗户和柔焦零售空间被自然日光照亮,不出现可读店铺文字。使用接近手机广角的略低于眼睛水平视角,眼睛位于上方三分之一并保持清晰对焦,背景柱子适度虚化;明亮高调自然日光形成柔和均匀的环绕光,暖肤色与冷白建筑形成清爽对比,保留自然皮肤纹理和轻微手机照片质感。排除未成年人、裸露、内衣、透明服装、性化姿势、胸部或身体部位特写、名人相似、logo、水印、可读文字、手机界面、多人、错误手指、畸形解剖、低清晰度和生成伪影。

English prompt

A 9:16 vertical lifestyle selfie photographed with a front-facing mobile camera, featuring one clearly adult original East Asian woman using character reference ref-10a-v1. She has a heart-shaped face, natural skin tone, long dark-chestnut hair with soft curtain bangs, one side naturally tucked behind the ear to show a silver stud, and a friendly confident closed-mouth smile with her head gently tilted right. She wears an opaque white long-sleeve button-down shirt, neatly fastened and draped naturally over a beige crew-neck underlayer. The styling is coverage-conscious, with no chest emphasis, transparent fabric, lingerie-like design, or brand marks. Add a simple silver-blue pendant and a blue beaded bracelet. She leans slightly forward for a selfie, holding the phone naturally in her right hand and the handle of a chartreuse shopping bag in her left. Both hands are clearly visible with five fingers each, relaxed and anatomically correct. Show the shopping bag and bracelet detail in the lower-left foreground; the midground shows the white shirt, beige underlayer, and pendant. The background is a bright modern luxury mall atrium with tall white pillars, polished floors, large windows, and softly blurred retail space lit by daylight, with no readable store text. Use a near-mobile-wide-angle view from slightly below eye level, place the eyes in the upper third with sharp focus, and softly blur the pillars behind. Bright high-key natural daylight creates even wrap illumination, with warm skin against cool white architecture and a subtle mobile-photo character. Preserve natural skin texture. Exclude minors, nudity, lingerie, transparent clothing, sexualized posing, chest or body-part emphasis, celebrity likeness, logos, watermarks, readable text, phone UI, multiple people, incorrect fingers, malformed anatomy, low resolution, and generative artifacts.

查看 API 模型

探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作

  • 莱雷海滩黄金时刻电影感人像

    泰国莱雷海滩黄金时段的超写实电影感齐腰旅拍肖像:以当前配置固定参考 ref-10a-v1 明确绑定模板中的第一人称“我”,人物穿宽松米白亚麻衬衫、经典太阳镜和简约腕表;背景为石灰岩悬崖及柔和虚化的碧绿安达曼海。完整保留自然发型、暖色肤调、海风、无修图质感及 85 mm 摄影要求。 | An ultra-realistic cinematic waist-up travel portrait at Railay Beach, Thailand: the currently configured fixed reference ref-10a-v1 is explicitly bound to t

  • 吃我一脚

    Photorealistic professional e-commerce photography, extreme low-angle frontal perspective directly facing the model's barefoot raised foot, the large sole and pointed toes fill the foreground with strong foreshortening, dramatic near-to-far perspective and visual pressure, elegant young woman with l

  • 1

    让材质更加干净整洁一些

  • 漫步欧洲街头的三格时尚画报

    垂直三格欧洲街拍时尚拼贴:以 ref-10a-v1 作为此可复用模板中女性主体的唯一面部身份参考;完整呈现街景、三种抓拍视角、服饰与配件、冰咖啡自拍及 Linkin Park 音乐播放器。面部特征按参考尽量保留,生成可能存在自然差异;64K 是高分辨率目标,不承诺实际像素尺寸。 | A vertical three-panel European street-style fashion collage using ref-10a-v1 as the sole facial identity reference for the female subject in this reusable te

  • 俯拍夜幕下的便利店街头肖像

    夜间街头时尚抓拍:从街对面较高楼层向下拍摄,一名年轻女子独自站在小型超市入口附近,略微偏离中心,呈现全身并保留开阔留白;穿白色 T 恤、水洗蓝色牛仔夹克、深色直筒牛仔裤和白色帆布运动鞋,单肩挂小手提袋。使用当前配置的固定面部参考 ref-10a-v1 作为本模板人物的面部参考。 | Candid night street-fashion scene viewed downward from an upper floor across the street: a young woman stands alone near a minimarket entrance, slightly off-c

  • 最喜欢的角色进食动作

    Add a food-specific eating action to the character in the configured reference image. Food is editable; defaults to a strawberry. The source mentions Nano Banana as its tool context. / 为配置参考图中的角色添加指定食物的进食动作;食物可编辑,默认一颗草莓。来源将 Nano Banana 作为工具语境提及。