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

圣诞姜饼跨框传递双联肖像

Christmas Gingerbread Passing Through Frames Diptych Portrait

以同一成年人物的左右双联画呈现圣诞姜饼传递动作,配以青绿色棚拍背景和明亮俏皮的叙事氛围。

圣诞姜饼跨框传递双联肖像 — AI image creation
圣诞姜饼跨框传递双联肖像

提示词 / Prompt

中文提示词

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. 创作一张并排的圣诞双联肖像,左右两个画面描绘同一位明确成年的the same clearly adult person, age 25+, depicted in both panels,面部身份均由配置参考图ref-10a-v1引导;保持整体可辨识一致,但不要承诺完全复制。左侧:人物戴圣诞帽,穿米色驯鹿图案毛衣,身体向右倾,将一块已咬过一口的姜饼人饼干越过中央分割线递出,并看向右侧。右侧:同一人物穿蓝色雪花图案毛衣,身体向左倾,张口作惊喜反应并伸手接饼干。两侧动作必须形成清晰连贯的传递关系。画面下方放置一个饼干铁盒,并在附近点缀少量散落的糖霜。使用明亮纯色bright teal棚拍背景、均匀明亮的平光和清楚的面部与手部细节,整体俏皮、温暖且具有小故事感。不要额外人物、文字、品牌标志或水印。

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. Create a side-by-side Christmas diptych showing the same clearly adult the same clearly adult person, age 25+, depicted in both panels in both panels, with facial identity in each depiction guided by configured reference ref-10a-v1. Keep the overall identity recognizably consistent without promising an exact copy. Left panel: the person wears a Santa hat and a beige reindeer-pattern sweater, leans to the right, looks toward the other panel and offers a gingerbread-person cookie with one bite taken out, reaching it across the center divider. Right panel: the same person wears a blue snowflake-pattern sweater, leans left, opens their mouth in a surprised reaction and reaches to receive the cookie. Make the handoff read as one clear, continuous playful action. Place a cookie tin near the bottom with a few scattered icing crumbs nearby. Use a bright solid bright teal studio backdrop and even, bright flat lighting with clear facial and hand details. Keep the mood playful, warm and narrative. No additional people, text, brand marks or 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

  • 橘红光影下的电影感极简人像

    A photorealistic 4:5, 2K studio portrait with a fitted matte-black pique polo, serious upward off-camera gaze, low-angle face-and-shoulders framing, orange-red gradient, dramatic shadows and rim light. / 4:5、2K 逼真影棚人像:哑光黑色珠地棉 Polo 衫、严肃且略向上的镜头外视线、低角度面部与肩部构图、橙红渐变背景、戏剧性阴影与轮廓光。

  • 红夹克女子四场景系列

    以同一位黑色短发、带雀斑、穿红夹克的年轻女子为主角,分别呈现城市、海滩、山脉和夜街四个环境;每张单独成图,并使用同一固定身份参考保持人物一致。

  • 吃西瓜的古怪年轻女性手绘编辑插画

    一位古怪的年轻成年女性在厨房桌旁吃西瓜,呈现半写实、松散有质感的传统手绘编辑插画;保留指定的发型、服装、姿势、神情、色彩和素描本质感。

  • 黑曜石玻璃悬浮全息幻彩产品摄影

    以可替换产品为主体,置于纯黑空间中居中悬浮;用黑曜石玻璃质感、内部体积辉光、焦散折射与强烈虹彩表现全息幻彩效果。示例默认值为掌上游戏机。

  • Fenty Beauty 五封邮件营销序列视觉模板

    将来源中的邮件序列请求整理为一张五栏视觉营销邮件模板板,保留欢迎、品牌理念、畅销产品、社交证明与首单优惠五个阶段及参考图中的美妆风格和主要文案。中英文提示词等义,优惠变量带有可复用默认值,并绑定工作流指定的人像参考。

  • 90年代中国乡野家庭童年抓拍

    可复用的竖版135胶片家庭生活照模板:表现90年代中国乡野普通家庭中孩子自然玩耍的一瞬,使用可替换的童年行为变量;保留日常抓拍的真实、随意与胶片偶然性。