OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
冷调精灵感成年女性棚拍人像
Cool-Toned Ethereal Studio Portrait of an Adult Woman
9:16正面证件照式成年女性棚拍特写，冷调灰紫妆容与银白碎刘海，浅灰无缝背景；右下角保留小型“voxcat”手写签名和同字隐性水印。
提示词 / Prompt
中文提示词
创作一张写实的9:16 vertical正面超近景棚拍肖像，主体为一位成年女性，面部身份由ref-10a-v1固定参考约束。构图严格对称稳定：完整保留发际至下巴的头部，仅留窄窄肩颈区域；端正的脸占画面大部分，双眼位于视觉中心并直视镜头。保留略短的窄鹅蛋脸，柔和收窄的下颌与末端微圆的短下巴；中等高度的平滑额头被刘海部分遮住；太阳穴自然饱满、苹果肌克制；小巧直鼻与精致窄唇。呈现浅灰棕至银灰色细直眉；中等偏大的长杏眼，外眼角微扬、窄双眼皮清晰，虹膜灰紫；目光平稳直视，睫毛细致分明，不夸张放大眼睛。采用冷调自然白肤色，底妆均匀轻透并保留真实纹理；小面积克制提亮与极轻修容；灰棕、藕粉、冷紫灰眼妆，低饱和粉杏腮红与裸玫瑰唇，同时保持自然真实的人类面部结构与皮肤纹理。人物气质冷静、精致、轻柔而略带疏离，只有轻微精灵感，绝不做卡通、动漫、二维或三维效果。发型：银白或冷灰白发色，中分轻薄碎刘海且不遮双眼，发丝顺滑柔软，发顶自然蓬松。服饰：肩颈仅露极少区域，穿简洁珍珠白、银灰色或干净高领哑光棚拍服装。拍摄采用与双眼同高的正面视角，85–105mm等效人像焦段并控制近拍畸变；大型柔光箱配轻微正面补光；纯浅灰至近白无缝背景。配饰极少且颜色浅；不要加入手、花朵、道具、环境叙事、动作故事或其他人物。避免广角畸变、夸张放大的眼睛、缩短鼻子、过尖下巴、幼态特征、塑料皮肤或重度磨皮。整体使用冷白、银灰与低饱和粉紫色调。在画面右下角加入准确文字“voxcat”，做成干净轻巧的小型英文手写签名，不抢面部主体；另保留一个低调、不易察觉的“voxcat”水印。不得出现其他字样、标签或标志。
English prompt
Create a photorealistic 9:16 vertical frontal extreme-close-up studio portrait of one adult woman, facial identity anchored to ref-10a-v1. Keep the composition strictly symmetrical and stable: the whole head from hairline to chin is visible, only a narrow shoulder/neck strip remains, the upright face fills most of frame, both eyes sit at the visual center and look directly into camera. Retain slightly short narrow oval face; soft tapered jaw with a short gently rounded chin; smooth medium forehead partly veiled by bangs; naturally full temples and restrained cheek volume; small straight nose and refined narrow lips. Render light grey-brown to silver-grey fine straight brows; medium-large long almond eyes with slightly lifted outer corners, narrow clean double lids and grey-violet irises; direct steady gaze, fine defined lashes, no exaggerated enlargement. Use cool natural-white skin with even translucent base and real texture; restrained small highlights, very light contour; grey-brown, lotus-pink and cool purple-grey eye makeup, low-saturation pink-apricot blush, nude rose lips and preserve natural human facial structure and skin texture. Style the adult as calm, refined, gentle and slightly aloof, with a subtle elfin character quality but never cartoonish, anime, 2D or 3D. Hair: silver-white or cool grey-white hair, center-parted wispy bangs that do not cover either eye, smooth soft strands and naturally airy crown. Clothing: only a minimal shoulder and neck strip in simple pearl-white, silver-grey or clean high-neck matte studio clothing. Shoot with eye-level frontal 85–105mm-equivalent portrait perspective with controlled close-up distortion; large softbox plus light frontal fill; plain seamless light grey to near-white background. Keep accessories minimal and pale, and do not add hands, flowers, props, scenery, action narrative or other people. Avoid wide-angle distortion, enlarged eyes, shortened nose, excessively pointed chin, juvenile features, plastic skin or heavy smoothing. Use cold white, silver-grey and low-saturation pink-purple tones. Add the exact text "voxcat" as a small clean handwritten English signature in the lower-right corner, understated and not competing with the face; also retain one subtle, hard-to-notice "voxcat" watermark. No other lettering, labels or logos.
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
相关作品
- 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