Thư viện prompt AI OpenZhenZhen · gpt-image-2.5 · image

Chân dung hai lớp phơi sáng lúc hoàng hôn trong phế tích

Double Exposure Profile at Sunset in Ruins

Chân dung hai lớp phơi sáng lúc hoàng hôn trong phế tích — khám phá tác phẩm được tạo bằng gpt-image-2.5 trên OpenZhenZhen, kèm prompt gốc và ví dụ tạo nội dung để tham khảo.

Chân dung hai lớp phơi sáng lúc hoàng hôn trong phế tích — AI image creation
Chân dung hai lớp phơi sáng lúc hoàng hôn trong phế tích

Prompt

Prompt tiếng Trung

使用已配置的 identity_reference ref-10a-v1 作为确切的个人肖像参考。保持同一可辨识的面部身份、自然面部结构、肤色、中性表情和直顺深色发型;不要替换人物或另造发型。创作超写实电影感双重曝光肖像,采用清晰的左向侧面轮廓,并呈现分明自然的下颌线。将深色、轮廓清晰的外部剪影置于柔和温暖的米色日落背景前。剪影内部无缝融合黄金时段的戏剧性城市废墟:同一人物独自在空旷的被毁城市道路中央向前行走,两侧受损建筑、人行道上的碎石,以及向远方延伸的电线杆和电缆呈对称透视。将太阳置于行走人物身后正对地平线的位置,形成强烈逆光光晕,并投下朝镜头延伸的长影。内部城市场景沐浴在温暖橙色阳光中,采用高反差和电影般纵深,呈现逼真纹理;肖像与环境之间平滑融合。整体氛围忧郁而充满希望。画面比例 4:5,细节锐利,以 8K 分辨率为目标,并加柔和暗角。

Prompt tiếng Anh

Use the configured identity_reference ref-10a-v1 as the exact personal portrait reference. Preserve the same recognizable facial identity and natural facial structure, skin tone, neutral expression, and straight dark hairstyle; do not substitute another person or invent a different haircut. Create an ultra-realistic cinematic double-exposure portrait in a clean left-facing side profile with a clearly defined natural jawline. Set the dark, well-contoured outer silhouette against a soft warm beige sunset background. Seamlessly blend a dramatic golden-hour urban ruin scene inside the silhouette: the same person walks forward alone at the center of an empty destroyed city road, with symmetrical perspective, damaged buildings on both sides, broken debris along the sidewalks, and utility poles and cables receding into the distance. Place the sun on the horizon directly behind the walking figure for a strong backlit glow and a long shadow stretching toward the camera. Fill the inner city scene with warm orange sunlight, high contrast, cinematic depth, realistic textures, and smooth blending edges between portrait and environment. Keep the mood moody yet hopeful. Compose for a 4:5 aspect ratio with sharp detail, an 8K-resolution target, and a soft vignette.

Xem mô hình API

Xem thêm prompt hình ảnh và video · Tạo hình ảnh · Tạo video · Tạo trên canvas AI