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

室内夜晚韩系女生抱兔玩偶快照

Indoor Night Korean Girl Hugging a Bunny Plush Snapshot

来自 OpenNana 的图像提示词，已按本地图像分类和站点 gpt-image-2.5 归类整理。 使用时需上传人物参考图；本流程使用统一参考人物生成示例。

室内夜晚韩系女生抱兔玩偶快照 — AI image creation
室内夜晚韩系女生抱兔玩偶快照

提示词 / Prompt

中文提示词

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。 9:16，压暗环境＋柔化闪光 bloom，室内夜晚女友视角快照，环境整体偏暗，柔化近轴闪光只轻轻托亮主体，高光带轻微 bloom 和柔润泛光，暗部仍保留头发和室内层次，背景暖黄灯串虚化。单人，成年韩系女生，桃粉甜美妆，眼下桃粉腮红明显，唇心微润，半哑光真实皮肤，鼻梁只有窄高光，双颊柔和漫反射，蓬松黑长发披肩。穿奶白薄针织上衣，略高俯视近景，坐在地毯或床边，怀里抱着一只奶白色兔子玩偶，手臂环住玩偶，脸微微靠近玩偶顶部。她轻轻鼓起嘴或抿嘴憋笑，带一点故意装可爱的神情，直视镜头。画面前景有柔软毛毯，后方有暖黄灯串、深棕懒人沙发和发光兔子夜灯。闪光重点落在眼下腮红、唇面、鼻梁细高光、发丝与针织纤维。不要油膜脸、过度磨皮、第二个人、肢体畸形、文字水印。

English prompt

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. 9:16, darkened environment + softened flash bloom, indoor night girlfriend perspective snapshot, the overall environment is dark, softened paraxial flash only lightly illuminates the subject, highlights with slight bloom and soft glow, dark areas still retain hair and indoor layers, background warm yellow string lights bokeh. Single person, adult Korean girl, peach pink sweet makeup, obvious peach pink blush under the eyes, slightly moist lip center, semi-matte real skin, only narrow highlights on the bridge of the nose, soft diffuse reflection on the cheeks, fluffy long black hair over shoulders. Wearing a creamy white thin knit top, slightly high-angle overhead close-up shot, sitting on a carpet or bedside, holding a creamy white rabbit plush in her arms, arms wrapped around the plush, face slightly close to the top of the plush. She gently puffs her cheeks or purses her lips to hold back a smile, with a slightly intentional cute expression, looking directly at the camera. Soft blanket in the foreground, warm yellow string lights, deep brown bean bag chair, and a glowing rabbit night light in the back. Flash focus falls on the blush under the eyes, lip surface, narrow highlights on the bridge of the nose, hair strands, and knit fibers. No oily face, over-smoothing, second person, limb deformity, text watermarks.

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

  • AI智能换装试穿对比海报

    A four-section 16:9 fashion try-on and pose showcase, using the configured generic identity reference, a coordinated outfit flatlay, a matching try-on result, and six poses.

  • 20 岁希娜时尚个性海报

    A vertical 9:16 Y2K street-fashion character poster using the configured generic face-identity input, with an adult Sheena design, irregular detail panels, and exact source metrics text.

  • 3×3 九宫格拼贴写真

    A cohesive 3×3 Korean playful studio portrait collage preserving the visible identity in the configured person reference across nine distinct poses and expressions.

  • 蓝莓主题可爱风人物海报

    A centered 3:4 blueberry-themed poster portrait using the configured generic face-identity reference, plush blueberry props, and exact source lettering.

  • 韩风手绘涂鸦感人物海报

    A Korean-style illustrated half-body portrait poster that preserves the visible identity in the configured person reference, with expressive ink-and-pastel doodle art.

  • 几何折纸蓝图风蜘蛛侠

    Hyper-detailed folded-paper SpiderMan blueprint preserving the source geometry, blueprint annotations, minimal paper-and-ink palette, studio lighting, crisp shadows, architectural-art style and photorealistic paper detail. The configured reference is attached only as the workflow-required generic id