OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
20 岁希娜时尚个性海报
Xina's Fashionable 20th Birthday Poster
A vertical 9:16 Y2K street-fashion character poster using the configured generic face-identity input, with an adult Sheena design, irregular detail panels, and exact source metrics text.

提示词 / Prompt
中文提示词
仅使用已绑定人物参考图作为面部身份参考,创作一张高质量竖版9:16希娜(Sheena)角色简介海报。主角为20岁成年潮流女性,带甜美wink和自信酷炫姿势;保留参考可见的可辨识面部身份、柔和五官与肤色。造型为棕色编辫发型、时尚街头服饰、层次配饰和厚底运动鞋;身高体重信息按指定文字呈现。 采用高端时尚编辑设计与Y2K街头风,使用铬色排版、动态纵深、丰富细节和干净利落的海报构图。主视觉突出人物,同时叠加不规则拼贴面板,分别展示眼睛、头发、脸部、手、腰部、腿部与鞋子的细节特写,各面板采用不同姿势、取景距离与角度;保持同一成年角色、造型和视觉连贯。锐利、时尚、精致、现代。服装得体,不暴露,不呈现幼态身材。 海报仅使用清晰英文文字,逐字准确呈现以下四项,不增删或改写: “SHEENA”、“AGE 20”、“165CM”、“47KG”。不要水印、Logo或其他无关文字。 负面要求:低质量、模糊、面部扭曲或身份错误、多余手指、坏手、解剖错误、重复身体、杂乱布局、文字不可读或拼写错误、水印、Logo、重度模糊、过曝或欠曝、塑料皮肤、AI伪影、不当或过度暴露服装、幼稚身材、变形鞋子、构图不良。
English prompt
Use the bound person reference only as a facial identity reference. Create a high-quality vertical 9:16 character profile poster for Sheena, an adult trend-conscious woman aged 20, with a sweet wink and a confident, cool pose. Preserve the recognizable visible facial identity, soft features, and skin tone from the reference. Style her with a brown braided hairstyle, fashionable streetwear, layered accessories, and chunky sneakers. Present the specified height and weight only as poster text. Use premium editorial design and Y2K street fashion, chrome typography, dynamic depth, rich detail, and a clean polished poster layout. Keep the character prominent and add irregular overlapping collage panels with distinct detail views of her eyes, hair, face, hands, waist, legs, and shoes; use different poses, camera distances, and angles in the panels while maintaining one consistent adult character, outfit styling, and visual treatment. Make it ultra-detailed, sharp, stylish, polished, and modern. Keep clothing appropriate and non-revealing; do not give her a childish body. Use clean English poster text only and render these four strings exactly, character for character, without additions or changes: “SHEENA”, “AGE 20”, “165CM”, “47KG”. Add no watermark, logo, or unrelated wording. Negative constraints: low quality, blur, distorted face, wrong identity, extra fingers, bad hands, broken anatomy, duplicate body, messy layout, unreadable text, misspellings, watermark, logo, heavy blur, overexposure, underexposure, plastic skin, AI artifacts, inappropriate or overly revealing outfit, childish body, deformed shoes, bad composition.
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