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

夕照和室中整理和服衣袖的成年女性胶片人像

Film portrait of an adult woman adjusting kimono sleeves in a sunlit Japanese room

成年东亚女性在传统榻榻米和室中整理完整和服的腰带与袖口，障子上的柔金圆形夕光构成背景视觉中心，呈现平成末期写真集般的复古胶片氛围。

夕照和室中整理和服衣袖的成年女性胶片人像 — AI image creation
夕照和室中整理和服衣袖的成年女性胶片人像

提示词 / Prompt

中文提示词

创作一张写实竖版3:4复古平成写真集风格人像，场景为传统榻榻米和室。画面中只有一位明确成年、25至32岁的东亚女性，面部身份绑定固定ref-10a-v1参考。她以端庄的四分之三侧身跪坐，轻轻整理完整穿着的腰带结与袖口；身穿深青绿色振袖和服，带克制的珊瑚色、白色与浅绿色花纹。和服穿着完整、交叠闭合且层次得体，领口端庄、内层不透明；不出现内衣或私密部位。深棕长发盘成利落低位和式发髻，配自然直刘海和一枚暗红色花饰。她稍微转头看向镜头，神情平静自持。身后障子纸门上映出边缘柔和的巨大金色圆形夕照，宛如月轮投影。环境包括榻榻米、深色木结构、低坐垫和少量折叠花纹布料，空间保持整洁克制。采用自然35至40毫米近景透视，机位略低但尊重主体，暖色定向夕光、深棕阴影与细腻35毫米胶片颗粒并存。保留真实肤质、和服垂坠与纸门纹理。整体为不挑逗的编辑人像；不要其他人物、可读文字、标志或水印。

English prompt

Create a photorealistic vertical 3:4 late-Heisei Japanese photobook-style portrait of one clearly adult East Asian woman, age 25–32, in a traditional tatami washitsu; bind her facial identity to the fixed ref-10a-v1 face reference. She kneels in a composed three-quarter side pose, gently adjusting the obi knot and sleeve of a fully worn, properly layered deep teal-green furisode kimono with restrained coral, white and pale-green floral motifs. The kimono is fully closed and secure, with a modest collar and opaque underlayers; no lingerie or exposed intimate areas. Give her long dark-brown hair in a neat low Japanese bun with natural straight bangs and one dark-red flower ornament. She turns her head slightly toward the camera with a calm self-possessed expression. Behind her, a shoji paper door carries a large soft-edged circular golden sunset glow, like a moon-wheel projection. Include tatami, dark wood, low cushions and a few folded patterned fabrics, keeping the room uncluttered. Shoot close with a natural 35–40 mm perspective, slightly low but respectful camera placement, warm directional sunset light, rich deep-brown shadows and fine 35 mm film grain. Preserve realistic skin, kimono drape and paper texture. Non-suggestive editorial portrait; no other people, readable text, logos or watermark.

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