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

Cắm hoa tại nhà ngày mưa

Rainy-day flower arranging at home

Cắm hoa tại nhà ngày mưa — 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.

Cắm hoa tại nhà ngày mưa — AI image creation
Cắm hoa tại nhà ngày mưa

Prompt

Prompt tiếng Trung

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。16:9 横幅,雨天下午的普通有人居住公寓,真实自然的手机随拍照片。一位成年女性,仅使用 ref-10a-v1 对应其面部身份,站在木质餐边柜旁,把一小束花整理进透明玻璃花瓶;花朵为柔粉与象牙白,带新鲜绿叶。她穿舒适、不透、不暴露的日常针织上衣与过膝宽松半裙,合身自然,不强调身体部位;姿态放松,没有摆拍感,视线落在花束上。餐边柜上有少量普通生活用品,前景露出餐桌一角,后方可见沙发和休息的猫;雨痕斑驳的窗户外隐约可见住宅楼。阴天窗光与室内柔和暖灯自然混合,保留可信的皮肤纹理和轻微真实摄影瑕疵。室内空间清楚可辨,采用普通主摄透视与平衡构图。不要人像模式虚化、魅惑式修图、性化造型、品牌标志或额外人物。

Prompt tiếng Anh

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. 16:9 landscape candid smartphone photograph in a modest, lived-in apartment on a rainy afternoon. One adult woman, using ref-10a-v1 only for her facial identity, stands beside a wooden sideboard and is arranging a small bouquet in a clear glass vase. The flowers are soft pink and ivory with fresh green stems. She wears a comfortable, opaque, modest knit top and a relaxed below-knee skirt; natural everyday fit, no body-part emphasis. Her posture is unposed and calm, eyes attending to the flowers. Include a few ordinary household details on the sideboard, a dining table edge in the foreground, a sofa and resting cat farther back, and a rain-streaked window with softly visible residential buildings outside. Blend cool overcast window light with gentle warm room lamps; preserve believable skin texture and natural photographic imperfections. Keep the room legible and in focus, ordinary main-camera perspective, balanced framing. No portrait-mode blur, glamour retouching, sexualized styling, logos, or added people.

Xem mô hình API

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