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

多人情绪肖像合成

Multi-Person Emotional Portrait Composite

9:16竖版超写实电影感合成肖像：中心人物安静持打开的书阅读，周围以前中后景分层呈现同一人物的多种情绪和自然手势。统一面部身份、发型、肤色与光线，暖色柔光、暗色简洁背景、紧凑人像构图；人物面部绑定指定参考图。

多人情绪肖像合成 — AI image creation
多人情绪肖像合成

提示词 / Prompt

中文提示词

以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下，保留来源的场景、造型、服装、姿势、构图、光线和视觉风格。制作一张9:16竖版、超写实且富有电影感的情绪合成肖像。画面表现同一位成年人物的多个同步分身：中心主像略靠前，穿简洁中性色休闲衬衫，手持打开的书安静阅读，神情平静专注；前景、中景和暗色简洁背景中的分身以紧密但清楚的层次围绕中心，分别呈现喜悦、震惊、好奇、恐惧、悲伤、困惑、兴奋、深思、愉悦与惊讶等不同表情，并以自然克制的手势表达情绪。所有分身必须是同一张参考面孔，保持一致的面部结构、发型和肤色；仅表情、轻微头部角度及视线方向变化，不改变身份。采用暖色柔和摄影棚光、微妙阴影和清晰眼神，呈现真实皮肤纹理与自然细节；紧凑取景，面部占据画面主体，85mm人像镜头观感与浅景深，中心读书人物清晰，后层仍能辨认表情。整体为写实摄影质感，不扭曲、不超现实夸张；背景保持深色简约，服装与色彩统一为米色、棕色与柔和蓝色。动作自然、层次分明，不让分身相互融合，不多出无关人物、肢体或文字。

English prompt

Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. Create a 9:16 vertical, photorealistic cinematic emotional composite portrait of multiple simultaneous versions of the same 成年人物. Place the central figure slightly forward, wearing 简洁中性色休闲衬衫, calmly reading an open book with a 平静专注 expression. Arrange the surrounding versions in clear foreground, middle, and rear layers against a dark minimal background; give each a different expression from 喜悦、震惊、好奇、恐惧、悲伤、困惑、兴奋、深思、愉悦与惊讶 and a restrained natural gesture. Every duplicate must retain the exact same reference identity, facial structure, hairstyle, and skin tone; vary only expression, slight head angle, and gaze. Use soft warm studio lighting, subtle shadows, expressive sharp eyes, natural detailed skin, and consistent light across all versions. Keep a tight face-led composition with an 85mm portrait-lens look and shallow depth of field: the central reader stays crisp while rear expressions remain recognizable. Maintain photorealism without distortion or surreal exaggeration. Keep clothing and color treatment coordinated in 米色、棕色与柔和蓝色. Separate the duplicates cleanly; do not fuse faces, add unrelated people or limbs, or introduce text.

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

  • 黑木崖红衣飞针傲立悬崖

    An original cinematic wuxia interpretation of the named fictional character, preserving the source's flying embroidery needles, red clothing, long hair, Heimuya cliff and blood-red sunset. The configured generic portrait is used only as the required face identity anchor, not as a canonical character

  • 李佳琦口红矩阵直播间背景

    A fictional, unoccupied livestream-commerce background with a lipstick matrix display wall, warm ambient lighting and the source's exact English visible copy. It does not claim to reproduce Li Jiaqi's actual studio. / 虚构的无人直播带货背景，包含口红矩阵展示墙、暖光氛围灯与来源要求的准确中文可见文案；不声称复刻李佳琦的真实直播间。

  • 复古报纸主角头版设计

    A realistic vintage newspaper cover placing the configured adult-woman portrait as the unchanged, recognizable central article photo, with fictional editorial text and print details. / 逼真的复古报纸头版，将配置的成年女性肖像作为保持原样且清晰可辨的中央主照片，并配以虚构编辑文字和印刷细节。

  • 地铁车厢抓拍低头看手机成年女性

    A respectful candid-style portrait of a fully clothed adult woman looking at her phone in a public subway carriage, with the original right-third subject placement and soft foreground obstruction. / 普通公共地铁车厢内，衣着完整的成年女性自然低头看手机；保留原有右侧三分之一人物布局和柔焦前景遮挡的抓拍构图。

  • 暖光咖啡馆里的蓝羽女孩

    A hyper-realistic cafe portrait of a seated adult woman in a light-blue feathered jacket, with a croissant in the foreground and crisp iPhone 15 Pro detail; exact appearance is reference-dependent.

  • 东方禅意海棠粉极简女性封面

    A gentle ancient-inspired adult-woman portrait framed by begonia-pink shadows, pearl white and quiet title space. / 以海棠粉花影、珍珠白背景与留白标题区衬托古风成年女性柔美肖像的极简封面。