OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
地铁车厢抓拍低头看手机成年女性
Candid shot of an adult woman looking down at her phone in a subway car
A respectful candid-style portrait of a fully clothed adult woman looking at her phone in a public subway carriage, with the original right-third subject placement and soft foreground obstruction. / 普通公共地铁车厢内，衣着完整的成年女性自然低头看手机；保留原有右侧三分之一人物布局和柔焦前景遮挡的抓拍构图。
提示词 / Prompt
中文提示词
仅将配置的 ref-10a-v1 用作一位成年女性可辨识面部与身份的锚点。不照搬参考图的裁切、服装或背景，保留来源所述的长发自然垂落。 在普通公共地铁车厢内，一位明确成年的女性坐在靠近车门的座位上，低头专注看手机，神态自然放松，不看向镜头。她衣着完整，穿灰色合身上衣、黑色短裙和白色运动鞋。 人物位于画面右侧三分之一，左侧保留柔焦前景遮挡，延续来源的随手抓拍构图。将画面呈现为普通公共场景中尊重、非侵入的日常瞬间，不带有秘拍或窥视意图。车门与扶手形成清晰的垂直线条，引导视线。 整体采用冷色调地铁灯光和柔和顶光，避免明显强烈阴影。用浅景深保持人物清晰，背景略微虚化。保留真实相机颗粒感与轻微不完美的构图，呈现自然随手抓拍的真实瞬间，而不是摆拍。
English prompt
Use configured ref-10a-v1 only to anchor the recognizable face and identity of one adult woman. Do not copy the reference crop, outfit or background. Preserve the source's long hair falling naturally. Inside an ordinary public subway carriage, one clearly adult woman sits on a seat near the door, looking down and focused on her phone in a natural, relaxed state, not looking at the camera. She is fully clothed in a gray fitted top, a black short skirt and white sneakers. Keep the subject in the right third of the frame. A softly blurred foreground obstruction remains on the left, preserving the source's candid snapshot composition. Frame this as a respectful, non-intrusive everyday public-scene moment, without a covert or voyeuristic implication. The subway door and handrails form clear vertical lines that guide the eye. Use cool-toned subway lighting and soft overhead light, with no obvious harsh shadows. Use shallow depth of field to keep the subject clear and the background slightly blurred. Retain natural camera grain and a slightly imperfect composition, like a real unposed snapshot rather than a staged portrait.
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。