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

深夜直闪下的成年女性复古胶片肖像

Vintage Film Portrait of an Adult Woman with Direct Flash at Midnight

25岁成年女性的夜间近景肖像：深棕色长波浪发由抬起的右手向后拨开，白色罗纹背心搭配水晶吊坠细金链与深樱桃红指甲；硬直闪令人物从漆黑夜色中凸显，保留真实皮肤和轻微胶片颗粒，身份绑定固定参考。

深夜直闪下的成年女性复古胶片肖像 — AI image creation
深夜直闪下的成年女性复古胶片肖像

提示词 / Prompt

中文提示词

创作一张写实的4:5夜间近景肖像：一位明确为25岁的成年女性。以已配置的人物身份参考作为面部身份依据，并保持她的可识别特征；不要强行指定与参考冲突的面部结构或眼睛颜色。她留着浓密的深棕色长发，发丝呈自然松散、略显凌乱的波浪状，抬起的右手将头发向后拨开，形成随性的抓拍瞬间。保留自然皮肤纹理、细微毛孔、柔软汗毛，以及鼻部和脸颊上零星雀斑；妆容轻盈水润。她微微张唇，神情自信并带些含蓄魅力，头部轻轻倾斜，直视镜头。指甲涂深樱桃红。她穿白色罗纹棉质背心，佩戴一条带小水晶吊坠的精致金链，呈现轻松的夜间出行穿搭。背景近乎漆黑，隐约暗示夜间街道或俱乐部入口。采用强烈机内直闪的视觉效果，面部高光明亮、眼睛清晰对焦、反差明显，光线迅速衰减融入黑暗。仅加入轻微自然胶片颗粒和细微色边，营造复古抓拍质感。氛围亲密自信但不作露骨表达。不增加其他人物、文字、标志或水印。不承诺精确相机、胶片、曝光参数或8K输出。

English prompt

Create a photorealistic 4:5 close-up nighttime portrait of one clearly adult 25-year-old woman. Use the configured identity reference as the guide for her facial identity and preserve her recognizable features; do not impose conflicting facial geometry or eye color. Style her long, voluminous dark-brunette hair in loose, slightly tousled waves, swept back by her raised right hand in a candid gesture. Retain natural skin texture with visible fine pores, soft peach fuzz and scattered freckles across the nose and cheeks; keep makeup light and dewy. Her lips are softly parted in a confident, subtly alluring expression, with a gentle head tilt and direct eye contact. Paint her nails dark cherry red. She wears a white ribbed cotton tank top and a delicate gold chain necklace with a small crystal pendant, styled as relaxed night-out fashion. Place her against a nearly black nighttime background suggesting a street or club entrance. Use a strong direct on-camera-flash look with bright facial highlights, crisp eye focus, high contrast and rapid falloff into darkness. Add only subtle organic film grain and slight chromatic edge fringing for a candid retro-film feel. Keep the mood intimate and confident rather than explicit. No extra people, text, logo or watermark. Do not promise exact camera/film-stock/exposure settings or 8K output.

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