OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

复古感九宫格时尚姿态研究

Retro Nine-Grid Fashion Pose Study

一张3×3时尚编辑九宫格,同一成年主体穿海军蓝与红色搭配的原创复古剪裁上衣,以九种手臂朝镜头延伸或自然放松的角度变化呈现于灰色影棚。

复古感九宫格时尚姿态研究 — AI image creation
复古感九宫格时尚姿态研究

提示词 / Prompt

中文提示词

创作一张精致的3列×3行时尚编辑摄影九宫格,由九张构图各异、尺寸统一并以整洁间距分开的照片组成。每格都是同一位与 ref-10a-v1 面部身份一致的成年主体;使用 ref-10a-v1 作为唯一人物身份参考,保持各格面貌一致。主体留丰盈后梳发型,神情自信,带克制的复古80年代气质。穿原创、端庄的海军蓝与红色拼搭剪裁上衣,带微妙水手领灵感、简约配饰和经典腕表;避免可识别的角色服装或特定系列造型。整组在中性灰背景的极简影棚拍摄,使用柔和漫射光、克制的色彩对比、自然清晰焦点和当代杂志质感。按阅读顺序呈现九种姿势:(1)正面人像,向镜头举起张开的手掌;(2)低角度四分之三侧面,手向前伸并形成强烈透视缩短;(3)俯拍全身,手臂朝镜头伸展;(4)背面视角,头部微转,手抬在半空;(5)清晰侧面轮廓,前景有一只手部分入画;(6)倾斜角度肖像,手靠近镜头形成俏皮透视;(7)极近特写,手自然遮住部分面部;(8)居中全身画面,手臂伸向镜头;(9)高角度视图,头部微垂、双手放松。手势保持俏皮但不接触他人,解剖自然、景别多变,同时九格身份统一。采用一般35–50毫米视角感,不宣称特定镜头。不要额外人物、文字、标志或水印;不要承诺超高分辨率。

English prompt

Create a polished 3-by-3 contact sheet of nine distinct high-fashion editorial photographs, with consistent panel sizes and clean gutters. The same adult subject matching the facial identity in ref-10a-v1 appears in every panel; use ref-10a-v1 as the identity reference for the sole subject and keep the face consistent. Give the subject voluminous brushed-back hair, a confident expression, and a restrained retro-1980s attitude. Dress them in an original modest navy-and-red tailored top with a subtle sailor-inspired neckline, minimal accessories, and a classic wristwatch; avoid any recognizable character costume or franchise-specific styling. Photograph the series in a minimalist studio against a neutral gray backdrop, using soft diffused light, controlled color contrast, crisp natural focus, and a contemporary magazine finish. Depict these nine poses in reading order: (1) front-facing portrait, open palm raised toward the camera; (2) low-angle three-quarter view, hand reaching forward with strong foreshortening; (3) top-down full-body view, arm extended toward the lens; (4) back view, head slightly turned, hand lifted in midair; (5) clean side profile with a hand partly entering from the foreground; (6) tilted portrait, hand near the lens for playful perspective; (7) extreme close-up with part of the face naturally obscured by a hand; (8) centered full-body frame, arm extended toward camera; (9) high-angle view, head tilted down and hands relaxed. Keep the gestures playful and non-contact, with natural anatomy and varied crops while preserving one consistent identity. Use a general 35–50 mm perspective look without claiming a specific lens. No extra people, text, logo, or watermark; do not promise ultra-high resolution.

查看 API 模型

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

  • 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

  • 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