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

鱼眼镜头下日本街头成年女性夜景人像

Night Portrait of an Adult Woman on a Japanese Street Through a Fisheye Lens

使用上传的身份参考图保持面部一致,拍摄一位明确成年的年轻女性在东京霓虹夜街中的全身超写实肖像;8mm 圆形鱼眼镜头带来 180° 视野、边缘变形和完美圆形黑色暗角。

鱼眼镜头下日本街头成年女性夜景人像 — AI image creation
鱼眼镜头下日本街头成年女性夜景人像

提示词 / Prompt

中文提示词

使用上传的身份参考图,保持面部身份一致。创作一张超写实的东京夜间街头全身人像:主体是一位明确成年的年轻女性,穿着精致的学院风街头服装,但不要呈现幼态或儿童化风格。使用 8mm 圆形鱼眼镜头,形成极端 180 度视野、强烈边缘变形和完美圆形黑色暗角。人物全身居中,双脚必须完整可见。将她置于霓虹灯照亮的东京街头,包含店面、招牌、红绿灯、路灯、湿润路面和可信的建筑细节;环境中的文字保持不可辨识,避免加入图形化文字。使用来自霓虹招牌、店面、红绿灯和路灯的柔和电影感夜间照明,形成真实反射、细腻皮肤高光和均衡曝光,避免高光过曝。呈现 Sony A7R V 级别、8mm f/3.5 圆形鱼眼视觉、ISO 1250、f/5.6、1/100 秒、HDR、锐利对焦、自然皮肤纹理、真实发丝、细致服装面料、专业街头摄影、8K 和 RAW 照片质感。避免未成年人、性化学院服装、脚部裁切、运动模糊、多余肢体、重复人物、标志、水印、可读文字和 AI 瑕疵。

English prompt

Use the uploaded identity reference to preserve the face consistently. Create an ultra-realistic full-body nighttime street portrait of a clearly adult young woman in Tokyo, wearing a polished school-inspired street outfit without childish styling. Shoot with an 8mm circular fisheye lens for an extreme 180-degree field of view, strong edge distortion, and a perfectly circular black vignette. Keep her full body centered and ensure both feet are fully visible. Place her on a neon-lit Tokyo street with storefronts, signs, traffic lights, streetlamps, wet pavement, and believable architectural detail; keep any environmental lettering unreadable and avoid added graphic text. Use soft cinematic night illumination from neon signs, storefronts, traffic lights, and lamps to create realistic reflections, subtle skin highlights, balanced exposure, and no blown highlights. Render Sony A7R V quality, 8mm f/3.5 circular fisheye look, ISO 1250, f/5.6, 1/100 second, HDR, sharp focus, natural skin texture, realistic hair, detailed clothing fabric, professional street photography, 8K, RAW-photo realism. Avoid minors, sexualized schoolwear, cropped feet, motion blur, extra limbs, duplicate people, logos, watermarks, readable text, and AI artifacts.

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