OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
成人从即时成像照片中浮现的错视肖像
Trompe-l'oeil portrait of an adult emerging from an instant photo
固定成人身份参考的3:4咖啡馆桌面错视构图：同一位穿着高领针织衫、中长裙和皮靴的女性从即时成像照片边框中自然延伸而出。
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。 创作一幅3:4竖版、照片级写实的强制透视错视照片：秋日巴黎街边咖啡馆的小桌上平放一张刚显影质感的即时成像照片，纸面有真实细微纹理与少量自然划痕。照片框内显示一位明确25岁以上成年女性的全身穿搭；同一位女性的上半身与头部仿佛越过相纸边框延伸到现实桌面，面部身份、发际线、发型和服装与参考图及框内影像完全一致，手自然向前伸出，动作轻松俏皮。她穿高领针织上衣、中长裙和皮靴，完整得体着装。相纸与桌面接触处及人物前方投下方向一致的真实柔和阴影，形成可信但不夸张的立体错视。画面以俯视三分之四近景构图，清晰对焦脸部和相纸，背景为柔和咖啡馆散景，可见小杯浓缩咖啡、秋叶与石板路。相纸底边印有清晰短标题“秋日记录”；相纸内用白色手写笔标注“高领针织衫”“中长裙”“皮靴”，箭头准确指向对应服饰，所有文字方向正常、不镜像、清楚可读。自然阴天光、写实皮肤纹理、真实纸面反光；不出现儿童、暴露穿搭、额外人物、商标、相机型号、水印或其他文字。
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 3:4 vertical photoreal forced-perspective optical-illusion photograph. On a small table at an autumn Paris sidewalk café lies a freshly developed-looking instant photo print with realistic paper texture and a few subtle natural scuffs. Inside the print, show the full outfit of one clearly adult woman, age 25+; the same woman's head and upper torso appear to extend naturally beyond the print border into the real tabletop scene. Her face, hairline, hairstyle, and clothing must match the uploaded reference and the printed image exactly. She reaches one hand gently forward in a playful, relaxed gesture. Dress her in a high-neck knit top, a modest midi skirt, and leather boots, fully clothed. Cast coherent soft real shadows where the print meets the table and in front of the emerging figure, creating a convincing but tasteful dimensional illusion. Use a close three-quarter top-down composition; keep her face and print sharp, with a soft café bokeh showing a small espresso cup, autumn leaves, and stone pavement. Print the short clear caption “AUTUMN NOTES” along the lower photo border. Inside the print, add white handwritten labels “knit top”, “midi skirt”, and “leather boots”, with arrows accurately pointing to each garment; all lettering must be upright, legible, and not mirrored. Use natural overcast daylight, realistic skin texture, and authentic paper reflections. No children, revealing styling, extra people, trademarks, camera-model names, watermark, or other text.
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
相关作品
- 人物与涂鸦结合的肖像照
A low-angle editorial portrait using the configured reference subject, styled with a pastel bucket hat, gray sweatshirt and round sunglasses beneath a doodle-filled blue sky. 使用当前配置参考中的人物创作低角度编辑风肖像，搭配马卡龙色渔夫帽、灰色卫衣和圆形墨镜，置于涂鸦点缀的蓝天下。
- 童话立体书奇幻主角照
A reference-based protagonist explores a cinematic handcrafted popup-book fairytale, rendered as a layered paper diorama viewed from above. 使用当前人物参考作为主角，在电影感手工弹出式童话书世界中探索；以俯视角呈现层叠纸艺立体模型。
- 高分辨率 Q 版克隆贴纸日记照
A centered real-person social diary portrait with a balanced ring of matching chibi stickers, light doodles and short handwritten English phrases. 使用真实人物居中的社交日记风人像，周围环绕外观匹配的Q版贴纸、轻盈涂鸦和英文手写短语。
- 4K 超高清时尚肖像
A luxury couture-inspired editorial mirror portrait using the configured generic identity reference, with cinematic studio lighting and premium fabric detail.
- AI智能换装试穿对比海报
A four-section 16:9 fashion try-on and pose showcase, using the configured generic identity reference, a coordinated outfit flatlay, a matching try-on result, and six poses.
- 20 岁希娜时尚个性海报
A vertical 9:16 Y2K street-fashion character poster using the configured generic face-identity input, with an adult Sheena design, irregular detail panels, and exact source metrics text.