OpenZhenZhen AI プロンプトギャラリー · gpt-image-2.5 · image

古風リアル韓系淡顔美女の雨窓撮影

Realistic Ancient-Style Korean Beauty by Rainy Window

「古風リアル韓系淡顔美女の雨窓撮影」は gpt-image-2.5 を使用した作品です。OpenZhenZhen で元のプロンプトと生成例を確認し、創作の参考にできます。

古風リアル韓系淡顔美女の雨窓撮影 — AI image creation
古風リアル韓系淡顔美女の雨窓撮影

プロンプト

中国語プロンプト

以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下,保留来源的场景、造型、服装、姿势、构图、光线和视觉风格。 3:4竖幅,古风写实人像摄影。一位明确成年的20多岁韩国女性,拥有精致韩系淡颜、鹅蛋脸、黑色古典盘发、淡紫色花饰和银色垂坠发簪,妆容水润自然。人物坐在古典亭台或临窗回廊,双手轻轻拢住一侧宽袖并靠近脸部,身体微侧,直视镜头,表情安静而略带若有所思,亲密但含蓄。 服装为雾紫色与浅薰衣草色汉服,带轻薄层叠长袖和大面积细腻花卉刺绣。左侧窗面布满清晰雨滴,窗外是柔和虚化的庭院、绿植和石景。冷灰蓝色雨天自然光从窗边照入,同时让人物肤色保持温暖,形成细腻的冷暖对比。使用浅景深,保留面部、眼神、发饰、袖口与刺绣细节,背景仍可辨识为雨中庭院。整体细腻、真实、克制,不要文字,不要拼图或拼贴。

英語プロンプト

Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. 3:4 vertical ancient-style realistic portrait photography of a clearly adult Korean woman in her 20s. She has refined Korean-inspired natural makeup, an oval face, a classical black updo, light-purple floral ornaments, silver dangling hairpins and dewy natural makeup. She sits in a classical pavilion or a window-side corridor, gently gathering one wide sleeve close to her face with both hands. Her body is slightly turned and she looks directly at the camera with a quiet, thoughtful expression that feels intimate but subtle. Dress her in mist-purple and light-lavender Hanfu with lightweight layered long sleeves and extensive delicate floral embroidery. The window on the left is covered with clear raindrops; outside is a softly blurred courtyard with greenery and stone scenery. Cold gray-blue rainy-day daylight enters from the window while the subject's skin remains warm, creating a delicate cool-warm contrast. Use shallow depth of field while preserving clear details in the face, eyes, hair ornaments, sleeve edges and embroidery, with the background still recognizable as a rainy courtyard. Keep the image delicate, realistic and restrained. No text, collage or split panels.

API モデルを見る

画像・動画プロンプトをもっと見る · 画像を生成 · 動画を生成 · AI キャンバスで作成