OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
中国地铁车厢女生生活抓拍写实人像
Candid Realistic Portrait of a Girl in a Chinese Subway Car
An adult woman photographs a three-line message on a phone in a modern subway, with distinct background passengers. / 成年女性在现代地铁车厢内以手机呈现三行文字，背景乘客彼此区分。
提示词 / Prompt
中文提示词
ref-10a-v1仅用于锚定这位明确成年的22岁东亚女性可辨识的身份；不要照搬参考图的裁切、服装或纯色背景。创作一张现代中国城市地铁车厢内的真实生活抓拍，由坐在车厢一侧的拍摄者横穿车厢拍摄。采用4:5竖版构图。拍摄者坐在长排座椅上，机位距地约90–110厘米、距人物约60–90厘米，以10–15度轻微低角度仰拍。将iPhone主摄1倍视角作为透视参考，不承诺实际拍摄元数据。采用居中近距离上半身构图，头顶完整入画，画面下缘裁切至连衣裙腰部以下。 主角：一位明确成年的22岁左右东亚女性，窄鹅蛋脸、柔和下颌线、清澈杏眼，面部略有自然不对称。保留自然内双、微扬眼尾；她越过手机上沿，略向下看着坐姿拍摄者，眼神放松。肤色白皙但保留毛孔和细微真实质感，妆容为日常通勤淡妆、天然平直眉、浅棕眼影与柔和睫毛。深棕黑色中长发自然披肩，中分八字刘海，额前有少量碎发，发尾微微内弯。身材丰满匀称，肩膀柔和偏窄，锁骨自然，手臂与腰纤细；保留来源对F罩杯体型的描述，不夸张解剖比例。 她穿暖象牙色、奶油白夏季细肩带连衣裙，平直方领露出肩颈与锁骨，上身合体束腰，腰以下裙摆自然散开。面料呈柔和微光的棉缎质感，胸前与腰侧有自然褶皱，裙摆顶部细密抽褶。左肩背一只厚实米白帆布托特包，包身落在画面左下方，宽布肩带自然垂落，并有黑、深棕、暗红色民族风几何刺绣。 她站在车厢中央过道，正对拍摄者，肩膀放松、上身略微前倾。右手将一部小米17 Pro Max竖直举在脸前，手机背面朝向拍摄镜头；手机上沿紧贴眼睛下缘，遮住鼻子、嘴、下巴和两侧大部分脸颊，只露出额头、完整眉眼和少量眼下皮肤。右手四根纤细手指自然握住手机中下部。左臂从左肩斜向伸至画面左上角，像要抓住上方扶手，左手伸出画框。保持真实肩肘关节和近距离透视。 手机背屏：呈现来源指定的小米17 Pro Max及其描述的一体化横向圆角矩形黑玻璃背屏。左侧在连续反光面板内纵向排列两枚大型黑色圆形摄像头。右侧浅粉白色圆角文字卡片约占面板宽度三分之二，四周留黑色边框。以小号清晰灰色无衬线字体，左对齐并准确完整显示以下三行中文：“哪站下车？”／“时间太长的话”／“我就换个人守着”。文字正向可读，卡片完整可见，尺寸符合真实屏幕；保留原文和标点。 人物对面是浅灰色地铁侧壁、横向车窗与窗外模糊深色隧道、银色扶杆、坐满乘客的长排座椅、浅色弧形顶板、通风格栅、接缝和冷白灯带。画面左下角另有一位深棕马尾、穿浅灰上衣的成年女性乘客低头坐着，身体自然被画框裁切；其余乘客作为次要背景人物。冷白顶灯均匀照明，肤色自然微暖、明暗过渡柔和，整体低饱和、低对比。保留真实手机随手拍质感、轻微噪点、适度算法锐化与压缩痕迹及自然室内曝光。除手机上的三行文字外不添加文字；不加水印。
English prompt
Use ref-10a-v1 only to anchor the recognizable identity of the clearly adult 22-year-old East Asian woman; do not copy its crop, outfit or plain background. Create a realistic candid photo inside a modern Chinese city subway carriage, viewed across the carriage by a seated photographer. Use 4:5 vertical framing. The photographer sits on a long row of seats; camera height about 90–110 cm from the floor and distance about 60–90 cm from the woman, with a 10–15 degree low upward angle. Treat iPhone main-camera 1x as a perspective cue, not guaranteed capture metadata. Frame a close upper body, centered, with her whole head visible and the lower edge below the dress waist. Main subject: a clearly adult East Asian woman, about 22, with a narrow oval face, soft jaw, clear almond eyes and slight natural facial asymmetry. Her natural inner-double eyelids, subtly raised eye corners and gaze are relaxed; she looks slightly down toward the seated photographer over the top of the phone. Keep fair skin natural with pores and subtle texture, daily-commute makeup, straight brows, light-brown shadow and soft lashes. Deep brown-black medium hair falls over her shoulders, center-parted curtain bangs, a few forehead flyaways and inward-curved ends. Her figure is full and proportionate, with soft narrow shoulders, natural collarbones, slender arms and waist; retain the source’s F-cup body description without exaggerating anatomy. She wears a warm ivory cream-white summer spaghetti-strap dress with a straight square neckline, shoulders and collarbones visible, fitted upper waist and a naturally flared skirt below the waist. Use softly lustrous cotton-satin texture, natural folds at chest and waist, and dense gathers at the skirt top. A thick off-white canvas tote hangs from her left shoulder into the lower-left frame, with wide straps and black, dark-brown and dark-red ethnic geometric embroidery. She stands in the center aisle facing the photographer, shoulders relaxed and torso leaning slightly forward. Her right hand holds a Xiaomi 17 Pro Max vertically close in front of her face, back toward the camera. The top of the phone sits just below her eyes, covering the nose, mouth, chin and most cheeks; leave forehead, brows, eyes and a little under-eye skin visible. Four slender right-hand fingers hold the lower-middle phone naturally. Her left arm reaches diagonally from the left shoulder to the upper-left edge as if grasping an overhead rail; the hand extends beyond the frame. Keep realistic arm joints and close perspective. Phone screen design: render the source-requested Xiaomi 17 Pro Max with the described integrated horizontal rounded-rectangle black-glass back-screen module. Two large black circular cameras sit vertically on the left within the same continuous reflective panel. On the right, a light pink-white rounded text card fills about two-thirds of the panel width, leaving a black border. Display these three Chinese lines exactly, left-aligned in small clear gray sans-serif type: “哪站下车？” / “时间太长的话” / “我就换个人守着”. Keep the card forward-readable, fully visible and realistically sized; preserve exact text and punctuation. Across the aisle, show the opposite light-gray subway wall, horizontal windows onto a dark blurred tunnel, silver rails, long occupied bench seats, curved pale ceiling, ventilation grilles, seams and cool-white light strips. A distinct background adult woman with a dark-brown ponytail and light-gray top sits at the lower left looking down, naturally cropped by the frame. Keep other passengers as secondary background figures. Cool-white ceiling fluorescents provide even light; skin remains slightly warm with soft transitions, low saturation and low contrast. Preserve realistic smartphone-snapshot texture, slight noise, moderate sharpening/compression traces and natural indoor exposure. No added text beyond the three phone-screen lines; no watermarks.
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
- 1girl
gpt image2.5生成
- 【超必杀】圣光白米大肥鱼
整体基调：东方史诗神话灾难大片质感，热血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，强烈金色侧逆光，体积沙尘，电影景深，动态运动模糊，节奏干脆迅猛。 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。 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，不是撕裂米粒浪潮喷涌过程，也不是爆炸过程，而是**米粒旋风接触虫王躯干的命中顶点瞬间，强行打断正常运动、插入极短静态定格画面的视觉卡点**。冲击帧仅0.2秒，帧内无
- 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
- 盛世长安万国来朝图
A text-driven historical reconstruction of the source scene: an aerial view of Kaiyuan-era Chang’an, Emperor Xuanzong and Yang Guifei looking out from Hanyuan Hall, and a distant tribute procession. The configured generic portrait is used only as a face-identity anchor for Yang Guifei in this genera
- 威震天高定西装时尚大片
A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面，保留银灰机甲、高定西装与赛博朋克霓虹场景；不声称复现某一改编版本的精确造型。