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

俏皮过肩回望与直闪时尚肖像

Playful Over-the-Shoulder Glance with Direct Flash Fashion Portrait

一位绑定固定身份参考的成年女性以俏皮皱鼻露齿表情回望镜头，右手搭在左肩，深棕半扎波浪发与深色微闪纹理服装在暖白墙前接受直闪照明，呈现利落的编辑时尚肖像。

俏皮过肩回望与直闪时尚肖像 — AI image creation
俏皮过肩回望与直闪时尚肖像

提示词 / Prompt

中文提示词

创作一张4:5竖版写实时尚编辑肖像。画面中只有一位成年女性，使用固定身份参考ref-10a-v1。从略高机位拍摄过肩姿势：身体转离镜头，同时回头看向镜头。表情俏皮又略带凶狠感，鼻子皱起、嘴巴微张并露出牙齿。她的右手搭在左肩，手指轻微绷紧，以几枚戒指和小型、非特定的细线手部纹身作为造型细节。深棕色头发蓬松地半扎半披并带柔和波浪；身穿得体的深色服装，呈现细微闪光的天鹅绒或蕾丝般纹理。背景为纯净的暖白色墙面。使用直射正面闪光形成利落的编辑高光与边缘清晰的硬阴影，同时保留自然皮肤质感。姿态与服装保持克制不露骨，主体清晰易辨。不得出现名人相似形象、其他人物、可读文字、标志、水印或特定相机/分辨率承诺。

English prompt

Create a photorealistic 4:5 vertical editorial fashion portrait of one adult woman, using the fixed identity reference ref-10a-v1. Frame her from a slightly high angle in an over-the-shoulder pose: her body turns away from the camera while she looks back toward the lens. Give her a playful, mock-ferocious expression with a scrunched nose and slightly open mouth showing teeth. Her right hand rests on her left shoulder, fingers gently tensed, with a few rings and small generic fine-line hand tattoos as styling details. Style her deep brunette hair in a voluminous half-up, half-down arrangement with soft waves, and dress her in a tasteful dark garment with subtle shimmering velvet or lace-like texture. Set the portrait against a plain warm off-white wall. Use direct frontal flash for crisp editorial highlights and distinct, hard-edged shadows while retaining natural skin texture. Keep the pose and garment non-explicit and the single subject clearly readable. No celebrity likeness, additional people, readable text, logos, watermark, or specific camera/resolution claims.

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