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

纸门前白色浴衣的日系近景肖像

Close-up Japanese portrait of a figure in a white yukata before a paper door

一位25岁以上的成年日本女性身穿领口得体的白色棉浴衣，在暖白纸门前拍摄的9:16近景肖像；唯一人物身份绑定配置的人脸参考。

纸门前白色浴衣的日系近景肖像 — AI image creation
纸门前白色浴衣的日系近景肖像

提示词 / Prompt

中文提示词

创作一张纵向9:16近景肖像：一位明确成年、25岁以上的日本女性，取景范围从胸部上方开始。将画面中唯一女性的面部身份绑定到已配置的ref-10a-v1参考图。她肤色白皙偏暖，脸颊自然泛粉，脸和下巴较小，深色单眼皮，鼻子小巧，嘴唇呈自然粉色。黑发松松地挽成低发髻，一缕发丝靠近太阳穴，脸颊旁有几缕柔软碎发。 她穿洁净的白色棉质浴衣，宽领整齐闭合并遮住锁骨。让下巴靠近镜头，同时保持端庄、非挑逗的呈现。眼睑自然放松，目光平静清澈；表情沉稳中性，嘴唇自然闭合。不要强调湿润感、裸露皮肤或性感气质。 使用约28厘米距离的近距离50mm镜头视角，脸部略向左倾，占据画面约93%，从头发和脸颊裁切至上胸部。背景纸门虚化成暖白色。柔和中性光从左侧窗户进入，嘴唇和眼角仅有克制的高光。整体色彩比例约为55%温暖白皙肤色、21%白色衣物、16%深色头发和8%背景；保留皮肤自然粉色，背景低饱和。即使在近距离透视下，也保持真实的面部比例与肌理。仅一位成年人物；不加文字、水印或解剖错误。

English prompt

Create a vertical 9:16 close-up portrait of one clearly adult Japanese woman, age 25+, framed from above the chest. Bind the sole visible woman's facial identity to the configured ref-10a-v1 reference. She has fair skin with natural warm pink cheeks, a small face and chin, monolid dark eyes, a small nose and natural pink lips. Her black hair is gathered in a loose low bun, with one strand near her temple and a few soft wisps by her cheek. She wears a clean white cotton yukata with a wide, neatly closed collar that covers the collarbones. Bring her chin near the camera while keeping the presentation respectful and non-suggestive. Her eyelids are gently relaxed and her eyes look calm and clear; use a composed neutral expression with lips naturally closed. Do not emphasize wetness, exposed skin or sensuality. Use a close 50mm-camera perspective from approximately 28 cm, with the face tilted slightly left and filling about 93% of the frame, cropped from hair and cheeks to the upper chest. Blur a shoji door into warm white behind her. Soft neutral light comes from a window on the left, with restrained highlights on the lips and eye corners. Keep the overall color proportions near 55% warm fair complexion, 21% white clothing, 16% dark hair and 8% background; retain natural pinkness in the skin and low saturation in the background. Preserve realistic facial proportions and texture despite the close perspective. One adult person only; no text, watermark or 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