OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
日本商场自动扶梯上的回眸抓拍
Candid Glance Back on a Japanese Mall Escalator
二十多岁的成年日本女性乘坐明亮商场内的上行扶梯，深巧克力色高马尾髻、黑色短款罗纹T恤与浅蓝宽松水洗牛仔裤；摄影者在她下方近处仰拍，她自然回头直视镜头，玻璃扶梯与暖色商铺光衬托出随性手机街拍感。
提示词 / Prompt
中文提示词
使用固定身份参考ref-10a-v1作为这位二十多岁、明确成年的日本女性的身份依据；不假定另有来源照片已附加。在明亮现代日本购物中心内创作一张写实竖幅2:3手机时尚抓拍。她乘坐玻璃侧板自动扶梯向上，身体先朝行进方向，随后自然转动躯干，越过一侧肩膀回望镜头，像是身后有人叫她。摄影者从她身后下方一至两级扶梯台阶的位置近距离略仰拍；面部清晰地位于画面上方三分之一，保留强烈前景透视但避免鱼眼变形。她的深巧克力色头发随意束成高马尾髻，搭配轻盈空气刘海和垂在脸颊旁的松散发丝。她穿合身黑色短袖罗纹短款T恤、高腰宽松浅蓝水洗牛仔裤，背小型挺括黑色肩包；造型休闲且稳妥。双臂自然放松，神情俏皮柔和，闭唇微笑。展现抛光不锈钢扶手、干净的白米色商场建筑、店铺入口与暖色内嵌灯光；远处购物者保持模糊且不可辨认。使用明亮柔和的商场光混合温暖店铺光，保留自然高光、真实皮肤与面料纹理、轻微手机计算摄影景深和克制锐化。整体像偶然抓拍，而非刻意摆拍或影棚照片。不出现可读品牌标牌、其他清晰可见人物、文字、标志或水印。
English prompt
Use the fixed ref-10a-v1 identity reference for the clearly adult Japanese woman in her twenties; no separate source photo is presumed attached. Create a realistic vertical 2:3 candid modern-phone fashion snapshot inside a bright contemporary Japanese shopping mall. She rides an upward-moving glass-sided escalator, body facing the direction of travel, then naturally twists her torso and looks back over one shoulder into the lens as if someone called her from behind. Photograph her closely from slightly below and one or two escalator steps behind; keep her face clear in the upper third and retain strong foreground perspective without fisheye distortion. Her dark-chocolate hair is gathered into a casual high ponytail bun with airy bangs and loose cheek-framing strands. She wears a fitted black short-sleeved cropped ribbed T-shirt, high-waisted loose light-blue faded jeans and a small structured black shoulder bag; keep the outfit casual and secure. Her arms rest naturally, her expression is a soft closed-lip playful smile. Show polished stainless-steel handrails, clean white-and-beige mall architecture, storefront entrances and warm integrated lighting. Keep any distant shoppers indistinct and non-identifiable. Use bright soft mall light mixed with warmer shop light, natural highlights, realistic skin and fabric texture, gentle computational-phone depth and restrained sharpening. Make it spontaneous rather than a deliberate fashion pose or studio image. No readable brand signs, extra visible people, text, logos or watermark.
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。