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

成年日本女性乡村电车全身抓拍

Full-body snapshot of an adult Japanese woman on a rural train

一张4:5照片级自然光抓拍:明确成年的日本女性坐在无人乡村电车的平行长凳座位上,从对面座位被完整拍到头到脚,鼓腮比耶,窗外是晴天蓝天下的彩色乡村景色。

成年日本女性乡村电车全身抓拍 — AI image creation
成年日本女性乡村电车全身抓拍

提示词 / Prompt

中文提示词

使用上传的身份参考,保持人物身份、脸部特征和自然比例一致;将人物明确表现为20岁的成年日本女性,不要使用少女化或未成年外观。创作一张纵横比4:5的照片级自然光抓拍,氛围像视频中的一个日常场景。人物坐在无人乡村电车车厢内、与行进方向平行的长凳式座位上,从对面平行座位以自然距离拍摄,完整纳入头到脚,脚和头都不裁切。她身材略显苗条,肤色白皙通透,黑发扎成单马尾,穿有图案的I型连衣裙。她直视镜头,鼓起脸颊并做和平手势,表情俏皮自然。车厢保持空旷,不出现男性面孔或其他乘客。窗外可见明亮多彩的乡村景色,带柔和散景;天气晴朗,蓝天清晰,明亮阳光洒入车厢,形成自然透视和真实车厢光影。画面自然、完整、非拼贴、非分割构图。不要站姿、斜构图、脚或头被裁切、昏暗车厢、雨天、主体脸部模糊、低分辨率、手部变形、异常手指数量、男性面孔、文字、标志或水印。

English prompt

Use the uploaded identity reference and keep the person's identity, facial features, and natural proportions consistent; depict the person as a clearly adult 20-year-old Japanese woman, with no youthful or minor-like presentation. Create a photorealistic 4:5 natural-light snapshot with the atmosphere of an everyday video scene. She sits inside an empty rural tram carriage on a bench-style seat parallel to the direction of travel, photographed from the opposite parallel seat at a natural distance. Capture her completely from head to toe without cropping either the feet or head. She is slightly slim, has translucent fair skin, black hair in a single ponytail, and wears a patterned I-line dress. She looks directly at the camera, puffs out her cheeks, and makes a peace sign with a playful natural expression. Keep the carriage empty, with no male faces or other passengers visible. Beautiful vibrant rural scenery appears outside the window with soft bokeh; the weather is sunny, the sky is blue, and bright sunlight pours into the carriage, creating natural perspective and realistic interior light. Keep the image single-frame, non-collage, and non-split. No standing pose, diagonal composition, cropped feet or head, dark carriage, rainy day, blurry subject face, low resolution, deformed hands, abnormal finger count, male faces, text, logos, or watermark.

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

  • 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。

  • 橘红光影下的电影感极简人像

    A photorealistic 4:5, 2K studio portrait with a fitted matte-black pique polo, serious upward off-camera gaze, low-angle face-and-shoulders framing, orange-red gradient, dramatic shadows and rim light. / 4:5、2K 逼真影棚人像:哑光黑色珠地棉 Polo 衫、严肃且略向上的镜头外视线、低角度面部与肩部构图、橙红渐变背景、戏剧性阴影与轮廓光。

  • 红夹克女子四场景系列

    以同一位黑色短发、带雀斑、穿红夹克的年轻女子为主角,分别呈现城市、海滩、山脉和夜街四个环境;每张单独成图,并使用同一固定身份参考保持人物一致。

  • 吃西瓜的古怪年轻女性手绘编辑插画

    一位古怪的年轻成年女性在厨房桌旁吃西瓜,呈现半写实、松散有质感的传统手绘编辑插画;保留指定的发型、服装、姿势、神情、色彩和素描本质感。

  • 黑曜石玻璃悬浮全息幻彩产品摄影

    以可替换产品为主体,置于纯黑空间中居中悬浮;用黑曜石玻璃质感、内部体积辉光、焦散折射与强烈虹彩表现全息幻彩效果。示例默认值为掌上游戏机。

  • Fenty Beauty 五封邮件营销序列视觉模板

    将来源中的邮件序列请求整理为一张五栏视觉营销邮件模板板,保留欢迎、品牌理念、畅销产品、社交证明与首单优惠五个阶段及参考图中的美妆风格和主要文案。中英文提示词等义,优惠变量带有可复用默认值,并绑定工作流指定的人像参考。