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

黑色上衣豹纹半身裙居家镜面穿搭照

Home Mirror Outfit Photo: Black Top and Leopard Print Skirt

A realistic vertical full-length mirror selfie of the configured adult woman identity in a black top and modest leopard-print skirt in a softly detailed home interior.

黑色上衣豹纹半身裙居家镜面穿搭照 — AI image creation
黑色上衣豹纹半身裙居家镜面穿搭照

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。创作一张9:16竖版全身镜面自拍，主体为一位明确成年的女性，面部身份绑定至已配置的ref-10a-v1。保留她具有辨识度的身份、发型和自然比例，不要臆造身份特征或夸张身材。她以放松平衡的姿态正对镜子站立，左手拿手机拍摄穿搭。服装为不透明修身黑色长袖上衣、及膝豹纹半身裙（带简洁侧边抽绳细节）和深色不透明连裤袜；整体舒适、得体且时尚，不使用透明拼片或造成皮肤压痕的紧绷效果。室内呈现自然生活空间：带竖向线条的米色衣柜、素白墙面、浅色木地板与白色仿毛地毯。采用自然直射室内光线和真实镜面反射，景深适中，使衣柜与房间纹理仍可辨认，并保留细微自然传感器颗粒。保持日常随拍手机照片感、手部准确、镜中全身映像完整且画面整洁。不要文字、标志、水印、额外人物、身份改变、情色姿势、身体部位强调、人工虚化效果或未经支持的设备/分辨率宣传。

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 realistic vertical 9:16 full-length mirror selfie of one clearly adult woman, with face identity bound to configured ref-10a-v1. Preserve her recognizable identity, hairstyle and natural proportions; do not invent identity-defining features or exaggerate body shape. She stands facing the mirror in a relaxed balanced posture, holding a smartphone in her left hand to take the outfit photo. Dress her in an opaque fitted black long-sleeve top, a knee-length leopard-print skirt with a simple side drawstring detail, and opaque dark tights; keep the styling comfortable, modest and fashion-forward, with no transparent panels or compression indentations. Set the scene in a lived-in home interior: beige wardrobe with vertical panel lines, plain white wall, light wood floor and a white faux-fur rug. Use direct natural indoor light with realistic mirror reflections, moderately deep focus so the wardrobe and room textures remain readable, and subtle natural sensor grain. Keep a candid everyday phone-photo aesthetic, accurate hands and a complete uncluttered reflection. No text, logos, watermark, extra people, altered identity, sexualized posing, body-part emphasis, artificial bokeh or unsupported device/resolution claims.

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