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

电梯里的薄荷绿恐龙连帽衫近景

Close-up of a mint green dinosaur hoodie in an elevator

一位明确年满25岁的成年女性以近景照片肖像呈现，身份绑定固定人物参考。高角度俯拍，她微微侧脸并抬眼望向镜头，带温和撅嘴和自然圆润脸颊；保留真实成年比例，不做Q版或婴儿化。她穿淡薄荷绿恐龙连帽连体衣，帽顶恐龙头部清晰可见，并用自己的双手轻扶帽沿。场景为现代电梯，金属墙面具有对称竖线，地面为浅色瓷砖；柔和均匀室内光、浅景深与清晰面部对焦营造温暖自然的抓拍氛围。

电梯里的薄荷绿恐龙连帽衫近景 — AI image creation
电梯里的薄荷绿恐龙连帽衫近景

提示词 / Prompt

中文提示词

创作一张4:5画幅的照片级近景人像，主体是一位明确年满25岁的成年女性，使用配置的人物身份参考ref-10a-v1。从明显的高位俯视角度拍摄，她专注地向上看镜头，脸微微侧转，带温柔俏皮的轻微嘟嘴和自然圆润的脸颊。保持真实成年面部比例与自然肌肤纹理，配柔和粉色腮红、玫瑰色自然唇妆和少量水润妆感；不要婴儿化、Q版或娃娃特征。她留及肩深棕色自然波浪发并自然分缝。她穿着舒适完整着装的淡薄荷绿恐龙连帽连体衣，帽顶恐龙头部清晰可见，即淡薄荷绿恐龙连帽连体衣，帽顶恐龙头部清晰可见；她用自己的双手轻轻扶住帽子两侧。场景位于现代电梯内，采用clean brushed-metal elevator walls with symmetrical vertical lines and a pale tile floor。使用柔和漫射室内光，均匀悦目的照明，无刺眼阴影；浅景深，面部超锐利对焦。整体甜美、温暖、好奇且自然，不带挑逗意味。不要其他人物、文字、标志或水印；避免卡通/动漫/CGI风格及过度磨皮。不承诺特定分辨率。

English prompt

Create a photoreal close-up portrait in a 4:5 frame of one clearly adult woman, age 25 or older, using configured identity reference ref-10a-v1. Shoot from a distinctly high, above-head angle as she looks intently upward toward the camera; turn her face slightly to one side and give her a gentle playful pout with naturally rounded cheeks. Keep realistic adult facial proportions, natural skin texture, soft pink blush, rosy natural lips and minimal dewy makeup; no baby-like, chibi or doll features. Her shoulder-length dark-brown hair is softly wavy with a natural part. She wears comfortable pastel mint-green dinosaur hooded onesie with a clearly visible dinosaur head on the hood, a pastel mint-green dinosaur hooded onesie with the dinosaur head clearly visible on the hood, and gently holds the sides of her hood with her own hands. Set the portrait inside a modern elevator with clean brushed-metal elevator walls with symmetrical vertical lines and a pale tile floor. Use soft diffused indoor light, even flattering illumination, no harsh shadows, shallow depth of field and ultra-sharp focus on her face. Keep the mood sweet, warm, curious and candid, not flirtatious. No other people, text, logos or watermark; avoid cartoon/anime/CGI styling and excessive smoothing. Do not promise a specific resolution.

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