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

暖光咖啡馆里的蓝羽女孩

Blue-Feathered Girl in a Warm-Lit Café

A hyper-realistic cafe portrait of a seated adult woman in a light-blue feathered jacket, with a croissant in the foreground and crisp iPhone 15 Pro detail; exact appearance is reference-dependent.

暖光咖啡馆里的蓝羽女孩 — AI image creation
暖光咖啡馆里的蓝羽女孩

提示词 / Prompt

中文提示词

生成一张超写实、极清晰的 iPhone 15 Pro 人像：成年主体坐在温暖昏暗的咖啡馆深色瓷砖桌旁，身体前倾，前景用放有大片酥皮可颂的盘子形成自然遮挡。主体穿浅蓝色吊带上衣和蓬松凌乱的浅蓝色羽毛外套，佩戴宽银色手镯与精致吊坠项链；留自然蓬松的长直金发，缎光底妆、低调中性唇彩，奶油般水润且可见毛孔的皮肤，数字纹理清晰。使用明亮 HDR 光线提亮阴影，同时保留咖啡馆温暖昏暗的氛围，整幅画面保持清晰对焦，不要背景虚化，画幅 3:4。仅将配置的 ref-10a-v1 用作一位成年女性可辨识身份与面部结构的锚点。按参考图可见范围保持整体比例，允许真实摄影中的自然变化；不推断参考中不可见的身体尺寸，也不照搬其裁切、服装、发型或背景。保留来源指定的长直金发和自然蓬松感。排除水印、标志、文字、签名、印章、版权、用户名、日期、模糊、低质量、畸形手部、融合五官、不自然解剖结构和 AI 瑕疵。

English prompt

Create a hyper-realistic, ultra-sharp iPhone 15 Pro-inspired portrait of the adult subject seated at a dark tiled table in a warm, dim cafe, leaning forward behind a plate holding a large flaky croissant. Dress the subject in a light-blue camisole beneath a voluminous shaggy light-blue feathered jacket, with a wide silver cuff and delicate pendant necklace; long straight blonde hair with natural volume, luminous satin makeup, subtle neutral lip gloss, creamy dewy skin with visible pores, and crisp digital textures. Use bright HDR lighting that lifts shadows while preserving the warm cafe atmosphere, keep the entire composition in crisp focus with no background blur, and use a 3:4 aspect ratio. Use configured ref-10a-v1 only to anchor the adult subject's recognizable identity and facial structure. Preserve overall proportions to the extent visible in the reference, allowing natural photographic variation; do not infer unseen body measurements or copy its crop, outfit, hair or background. Keep the source-directed long straight blonde hair with natural volume. Exclude watermark, logo, text, signature, stamp, copyright, username, date, blur, low quality, distorted hands, fused features, unnatural anatomy, 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