OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
原创成年模特四格时尚风格研究
Original Adult Model Four-Panel Fashion Style Study
原创成年时装模特的四格风格研究拼贴，分别呈现黑白剪裁、日落红裙、现代结构主义与波西米亚花卉长裙。
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。 制作一张2×2时尚风格研究拼贴，主体为an original fictional adult fashion model，一位原创虚构的成年模特。四格中保持同一张可辨认的脸、成年年龄特征和整体身份；不得模仿或描绘安娜·德·阿玛斯或任何其他公众人物。每格采用明确不同的编辑时尚美学，同时维持统一、专业的设计板布局。 左上：高对比黑白人像，穿剪裁利落、带缎面翻领的黑色礼服西装和挺括褶裥衬衫，头发向后梳，双手叉腰，自信沉稳。右上：黄金时段户外肖像，穿领口端庄、造型优雅含蓄的飘逸深红缎面礼服，微风带动裙摆，背景为柔和虚化的城市天际线。左下：现代前卫造型，穿结构感不对称黑白中长裙，以粗粝混凝土墙为背景，姿态呼应建筑线条。右下：温柔波西米亚人像，模特穿复古花卉长裙坐在窗边，由柔和逆光照亮。 四格边界清晰，协调各自的反差、色彩和光线，使风格一目了然。表情从容，服装不暴露，人体比例自然。不模仿名人，不出现文字、标签、标志或水印。输出4:5。
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 polished 2-by-2 fashion-style study featuring an original fictional adult fashion model, an original fictional adult model. Keep the same recognizable face, adult age appearance and overall identity in all four panels; do not imitate or depict Ana de Armas or any other public figure. Give each panel a clearly distinct editorial aesthetic while maintaining a consistent professional fashion-board layout. Top left: high-contrast black-and-white portrait in a sharply tailored black tuxedo with satin lapels and a crisp pleated shirt, slicked-back hair and confident hands-on-hips pose. Top right: golden-hour outdoor portrait in a flowing crimson satin gown with a modest neckline and elegant covered styling, wind moving the fabric against a softly blurred city skyline. Bottom left: modern avant-garde look with a structured asymmetrical black-and-white midi dress against raw concrete, posed with calm architectural lines. Bottom right: gentle bohemian portrait seated by a window in a vintage-inspired floral maxi dress, warmed by soft backlight. Separate the four panels cleanly and balance their contrast, color and lighting so each style reads immediately. Keep expressions poised, clothing non-revealing and anatomy natural. No celebrity likeness, text, labels, logos or watermark. Output 4:5.
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
相关作品
- 吃我一脚
Photorealistic professional e-commerce photography, extreme low-angle frontal perspective directly facing the model's barefoot raised foot, the large sole and pointed toes fill the foreground with strong foreshortening, dramatic near-to-far perspective and visual pressure, elegant young woman with l
- 1
让材质更加干净整洁一些
- 漫步欧洲街头的三格时尚画报
垂直三格欧洲街拍时尚拼贴：以 ref-10a-v1 作为此可复用模板中女性主体的唯一面部身份参考；完整呈现街景、三种抓拍视角、服饰与配件、冰咖啡自拍及 Linkin Park 音乐播放器。面部特征按参考尽量保留，生成可能存在自然差异；64K 是高分辨率目标，不承诺实际像素尺寸。 | A vertical three-panel European street-style fashion collage using ref-10a-v1 as the sole facial identity reference for the female subject in this reusable te
- 俯拍夜幕下的便利店街头肖像
夜间街头时尚抓拍：从街对面较高楼层向下拍摄，一名年轻女子独自站在小型超市入口附近，略微偏离中心，呈现全身并保留开阔留白；穿白色 T 恤、水洗蓝色牛仔夹克、深色直筒牛仔裤和白色帆布运动鞋，单肩挂小手提袋。使用当前配置的固定面部参考 ref-10a-v1 作为本模板人物的面部参考。 | Candid night street-fashion scene viewed downward from an upper floor across the street: a young woman stands alone near a minimarket entrance, slightly off-c
- 最喜欢的角色进食动作
Add a food-specific eating action to the character in the configured reference image. Food is editable; defaults to a strawberry. The source mentions Nano Banana as its tool context. / 为配置参考图中的角色添加指定食物的进食动作；食物可编辑，默认一颗草莓。来源将 Nano Banana 作为工具语境提及。
- 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。