OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
繁华古街回头一瞥的东亚女性
An East Asian Woman Glancing Back on a Bustling Old Street
成年女性在繁华中国传统商业街行走时回头看向手机的写实街头时装抓拍，包含浅粉色罗纹上衣、白色挎包、红灯笼与午后自然光。使用时上传人物参考图。
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。 一张完全自然、写实的智能手机抓拍照片，记录了一位年轻的东亚女性在白天走过繁华的中国传统商业街。镜头从斜后方拍摄，她自然地转过头，越过肩膀看向手机相机，就像朋友在走路时随手拍的一样。她留着黑褐色的长发，扎成蓬松凌乱的丸子头，鬓角和脸颊旁散落着柔软的发丝，阳光下隐约可见几根飞扬的头发，皮肤白皙自然，化着极简的日常妆容，双唇呈淡淡的粉红色，表情平静且带有好奇感。她穿着一件修身的浅粉色罗纹短袖上衣，肩上自然地背着一个白色挎包。在她身后是一条真实的旧商业街，有着传统的中国店面、木质建筑、许多挂着的红灯笼、朝不同方向行走的行人、店铺招牌、人行道，建筑物之间隐约可见远处的城楼。明亮的自然午后阳光，写实的阴影，略微不均匀的曝光，移动人群产生的轻微背景动态模糊，自然的景深，真实的智能手机HDR，微妙的镜头畸变，边缘处略显柔和，真实的皮肤毛孔，根根分明的发丝，自然的织物纹理，不完美的构图和对焦，平凡的街道细节，无电影感调色，无摄影棚灯光，无美颜滤镜，无过度修图，不追求完美对称，无人工锐化。使其看起来像是一张由朋友用现代手机拍摄的真实自发照片，带有微小的瑕疵和写实的计算摄影处理，极具真实感且与真实照片无异，竖向4:5构图。
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. A completely natural, photorealistic smartphone snapshot of a young East Asian woman walking through a busy traditional Chinese shopping street during the daytime. She is captured from slightly behind as she turns her head naturally over her shoulder toward the phone camera, as if a friend casually photographed her while they were walking. She has dark brown-black hair tied into a loose messy bun, with soft wispy strands falling around her temples and cheeks, a few flyaway hairs visible in the sunlight, natural fair skin, minimal everyday makeup, subtle pink lips, and a calm curious expression. She wears a fitted pale pink ribbed short-sleeve top with a white shoulder bag hanging naturally from her shoulder. Behind her is a real-looking old commercial street with traditional Chinese storefronts, wooden architecture, many red hanging lanterns, pedestrians walking in different directions, shop signs, pavement, and a distant city tower visible between the buildings. Bright natural afternoon sunlight, realistic shadows, slightly uneven exposure, mild background motion blur from moving people, natural depth of field, authentic smartphone HDR, subtle lens distortion, slight softness around the edges, realistic skin pores, individual hair strands, natural fabric texture, imperfect framing and focus, ordinary street details, no cinematic color grading, no studio lighting, no beauty filter, no excessive retouching, no perfect symmetry, no artificial sharpness. Make it look like an actual spontaneous photo taken on a modern phone by a friend, with tiny imperfections and realistic computational-camera processing, highly believable and indistinguishable from a real photograph, vertical 4:5 composition.
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
- 暗黑大肥鱼
整体基调：东方史诗神话灾难大片质感，暗黑恶魔动漫爆发感融合好莱坞写实CG，UE5电影渲染，HDR光追，真实物理，强烈黑金色侧逆光，深红体积沙尘与恶魔烟尘，电影景深，动态运动模糊，节奏干脆迅猛，黑红金主色，地狱化战场氛围。 图1锁定角色：蓝渐变长卷发，头顶呆毛，鲸鲨鱼耳，鲸鲨长尾，女仆裙装，白色围裙，围裙印有小鲸鱼图案，Q版比例。角色造型保持不变，但整体气质改为暗黑恶魔审判者感，表情冷冽、嘲弄、残忍，动作像恶魔刽子手执行处刑。 图2锁定巨型黑黄条纹甲壳虫王，巨口獠牙、尖刺前爪、虫群头领气质。 图3只用于冲击帧视觉语言【严格遵循Impact Frame规则】：冲击帧不是连续动画，不是撕裂米粒
- 特斯拉电动车核心部件示意全景
横向概念示意海报：以未指定车型的特斯拉电动车为中心，周围安排若干模块放大细节。电池包、电驱电机、逆变器/电力电子、车载充电器、热管理回路、悬架与制动、充电接口均为整理者选定的示意模块，不是来源列明的清单，也不代表特定车型布局或工程规格。 / A landscape conceptual overview centered on a Tesla EV of unspecified model, surrounded by selected module detail callouts. Battery pack, drive motor, inverter/power electronics,
- 日系负片里的记忆碎片
A 9:16 candid Japanese negative-film style portrait. The adult person, unposed walk and quiet neighborhood lane are replaceable curator-selected defaults, not subject or scene details supplied by the source. The currently configured ref-10a-v1 is used as the generic person identity reference and is
- 1girl
gpt image2.5生成
- 法式风情地标美食海报
A premium, clean and elegant poster concept built from the source’s broad request. Eiffel Tower, Arc de Triomphe, ratatouille and Provençal bouillabaisse are curator-selected illustrative examples, not details stated by the source; they can be replaced in a future variant. The source example image i
- 梦回江户浮世绘古典人物像
A reference-led Edo-period ukiyo-e portrait transformation that preserves the supplied person’s facial identity while restyling hair, clothing and accessories in traditional Japanese fashion. The current ref-10a-v1 is the generic person preview for this workflow, not a claim about any external named