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

深蓝影棚中的四格鱼眼多视角肖像

Four-Panel Fisheye Multi-Angle Portrait in a Deep Blue Studio

一张2x2四格影棚人像，明确成年的同一位人物穿深红飞行员夹克、蓝色牛仔裤和白色无品牌高帮鞋，四格分别展示中景、特写、俯视和从鞋面向上的超低角度鱼眼视角，并加入白色手绘涂鸦。

深蓝影棚中的四格鱼眼多视角肖像 — AI image creation
深蓝影棚中的四格鱼眼多视角肖像

提示词 / Prompt

中文提示词

使用参考人物 ref-10a-v1，创作一张完整背景覆盖的2x2四格影棚人像网格，不使用圆形取景。四个画面都呈现同一位明确成年的时装人物，穿深红色飞行员夹克、蓝色牛仔裤和白色无品牌高帮运动鞋；服装完全不透明、端庄、非性化。四格依次展示中景、特写、向下看的俯视角度，以及从鞋面向上看的超低角度，每格都使用鱼眼镜头透视和适度透视缩短，人物摆出不同但自然有趣的面部表情与姿态。每个画面周围都加入白色手绘涂鸦元素。背景是覆盖整个画面的深蓝色影棚，保持人物身份、服装和色彩一致。采用清晰影棚光、真实面料、自然皮肤纹理和有趣的编辑式构图。避免品牌标志、文字、水印、额外人物和解剖错误。

English prompt

Use reference person ref-10a-v1 to create a full-background 2x2 four-panel studio portrait grid with no circular framing. All four panels show the same clearly adult fashion subject wearing a dark-red bomber jacket, blue jeans, and white unbranded high-top sneakers; the clothing is fully opaque, modest, and non-sexualized. The panels respectively show a medium shot, a close-up, a high angle looking down, and an extreme low angle looking upward from the sneakers. Use a fisheye-lens perspective and controlled foreshortening in every panel, with a different but natural playful facial expression and pose in each. Surround the subject with white hand-drawn doodle elements in every panel. Use a dark-blue studio background that fills the entire image, keeping the identity, outfit, and colors consistent. Use clear studio lighting, realistic fabric, natural skin texture, and a playful editorial composition. Avoid brand logos, text, watermarks, extra people, and anatomy errors.

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