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

东亚女性海上游轮旅行街拍

East Asian Woman Street Photography on a Cruise Ship

成年女性海上游轮旅行街拍：使用统一人物参考图保持面部身份，人物站在船舶甲板上迎风看海，穿蓝色牛仔夹克与棕灰宽檐软帽，船尾航迹和开放海面构成自由的手机抓拍场景；仅保留指定文字 Soran。

东亚女性海上游轮旅行街拍 — AI image creation
东亚女性海上游轮旅行街拍

提示词 / Prompt

中文提示词

使用上传的参考图作为画面中可见成年女性的面部身份依据，保留她可辨认的面部身份与自然比例，同时保持旅行造型自然、普通且像抓拍。 创作一张竖幅 3:4 的真实手机旅行快照：她站在正在航行的客船开放甲板上。使用中广角构图，在海面方向保留充足留白；人物身体略微前倾，一只手扶住甲板设施，另一只手向右上方高举，形成自然倾斜的肩线。深棕黑色长发被海风吹动，穿宽松中蓝色牛仔夹克和简洁内搭，戴棕灰色宽檐软帽。她自然微笑，只偶尔短暂接触镜头，主要看向海面或船尾航迹，不要摆拍感。 展现晴朗蓝天、灰蓝海面、船尾清晰白色航迹、可信的船体结构，以及少量旗帜或彩带。使用明亮自然日光和帽檐轻微阴影，保持暖肤色、牛仔蓝、天空蓝、海水蓝灰与克制棕色点缀。人体比例、肩部、手部和手指自然正确，画面明确处于航行状态，传达开放和自由感。保留真实手机旅行照片的轻微镜头畸变与自然瑕疵，不要 HDR 过度处理、强锐化或商业磨皮。 将精确单词“Soran”作为唯一允许出现的可读文字，以三种材质尺度融入画面：在脸旁的牛仔衣领、胸前口袋或帽带处清晰可读的刺绣；隐藏在牛仔斜纹、帽子织纹、头发走势、船体细划痕或缆绳纤维中的细节；以及由牛仔车线、金属铆钉、船体螺栓、绳结和航迹泡沫排列暗示的微观文字。所有重复都必须像物理材质自然形成，不能像贴上的 logo。不要加入其他可读文字、标志、水印、贴纸 logo、漂浮文字或字幕。 避免反复直视镜头、僵硬摆姿、过度电光蓝天空、牛仔与天空完全融为一色、帽檐遮住眼睛、肩关节错位、手臂过长、手指变形、缺失航迹、海平面严重倾斜、过多旗帜彩带、塑料皮肤和过度广告化修图。

English prompt

Use the uploaded reference image as the facial identity reference for the visible adult woman. Preserve her recognizable facial identity and natural proportions while keeping the travel styling candid and ordinary. Create an authentic vertical 3:4 mobile travel snapshot of her on the open deck of a moving passenger ship. Keep a medium-wide composition with clear negative space toward the sea: she leans slightly forward, one hand holds a deck fixture and the other lifts high toward the upper right, creating a relaxed tilted shoulder line. Her deep brown-black long hair blows in the sea breeze. She wears a loose medium-blue denim jacket over a simple inner layer and a wide soft brown-gray floppy hat. Give her a natural happy smile, with only occasional partial eye contact; she should mostly look toward the sea or the wake rather than pose for the camera. Show a clear blue sky, gray-blue sea, white wake at the stern, believable ship structure and only a few flags or ribbons. Use bright natural daylight with a light hat-brim shadow, warm skin tones, denim blue, sky blue, sea blue-gray and restrained brown accents. Keep the body anatomy natural, hands and fingers correct, and the scene open, free and unmistakably underway. Preserve a realistic smartphone look with slight lens distortion and natural imperfection, not HDR, heavy sharpening or commercial retouching. Integrate the exact word "Soran" as the only allowed readable text at three material scales: clearly readable embroidery near the face on the denim collar, chest pocket or hat strap; subtle hidden instances in denim twill, hat weave, hair flow, hull scratches or rope fibers; and tiny instances suggested by denim stitching, metal rivets, ship bolts, rope knots and wake foam. These repetitions must feel physically embedded, not pasted logos. Do not add any other readable text, logo, watermark, sticker, floating text or subtitle. Avoid repeated direct gaze, stiff posing, electric-blue sky, denim merging completely with sky, hat covering the eyes, dislocated shoulders, overlong arms, malformed fingers, missing wake, severely tilted horizon, excessive flags, plastic skin and over-edited advertising polish.

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