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

复古东亚女性镜面人像与樱桃静物

Vintage East Asian Woman in Mirror Portrait with Cherry Still Life

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。

复古东亚女性镜面人像与樱桃静物 — AI image creation
复古东亚女性镜面人像与樱桃静物

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。 1:1方幅,东亚女性,暖暗复古室内镜像近景人像,深棕黑中长至长发自然松散垂落,人物低伏在桌面或梳妆台边缘,上身贴近镜子,一条前臂横向伸展,双手自然叠放在古典椭圆镜上缘附近,头部侧向前伸,现实人物低头看向镜面或画面左下,不直接看镜头,安静、沉浸、略微出神。 下半画面放置一面厚重古典椭圆桌镜,旧银或暗金雕花金属镜框,卷草纹与花卉纹明显,镜中必须准确反射同一个人物,同一张脸、同一发型、同一瞬间,镜中倒置人脸完整可辨,镜面反射方向与现实人物姿态严格一致,双手、脸部与镜框遮挡关系真实,不出现额外人物或第三张脸;镜面自然散落约6至10颗鲜红樱桃,部分带绿色细果梗,分布松散不规则,红色果实围绕镜中脸形成小面积视觉节奏。 左前上方暖色柔光照亮现实人物脸部、手背和镜框边缘,深色长发与背景压入暖棕暗部,镜面保持低亮柔反射,樱桃表面出现小面积湿润高光,暖棕、柔肤色、旧金米色、樱桃红主色,50至85mm近景感,soft focus,warm diffusion,low contrast,film grain,轻halation,slight bloom,vintage lens softness,soft highlight roll off,旧电影、旧杂志、复古静物肖像质感,现实脸、镜中脸、手、镜面与樱桃统一柔化。 清晰可读Soran融入靠近人物手部的古镜雕花边框,以旧银或暗金金属刻字沿椭圆镜框曲率自然弯曲;隐藏Soran融入镜框卷草纹、长发发丝、樱桃果梗走势、桌面木纹、镜中高光;微观Soran由镜框磨损点、樱桃高光、发丝交叉、金属细划痕、果梗节点组成。 负向:镜中不同人物,多张脸,第三张脸,倒影方向错误,镜像五官错位,手与倒影不对应,镜框穿过脸或手,多指,手指粘连,樱桃数量过多,樱桃整齐排列,现代无边框镜,LED化妆镜,人物抬头强直视镜头,甜笑,镜中倒影过锐,商业棚拍,整体橙黄滤镜过重,HDR,8K超锐,塑料皮肤,商业磨皮,外贴水印,贴纸logo,漂浮文字,字幕,不可读Soran。

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. 1:1 square ratio, East Asian female, warm dark vintage indoor mirror close-up portrait, deep brown-black medium-to-long hair naturally and loosely falling, figure leaning low on the edge of a table or dressing table, upper body close to the mirror, one forearm extended horizontally, hands naturally stacked near the upper edge of a classical oval mirror, head tilted forward, real person looking down towards the mirror surface or the lower left of the frame, not looking directly at the camera, quiet, immersive, slightly tranced. A heavy classical oval table mirror is placed in the lower half of the frame, with an old silver or dark gold carved metal frame, acanthus and floral patterns are obvious, the mirror must accurately reflect the same person, same face, same hairstyle, same moment, the inverted face in the mirror is complete and recognizable, the mirror reflection direction is strictly consistent with the real person's posture, the occlusion relationship between hands, face, and mirror frame is realistic, no extra characters or a third face appear; about 6 to 10 bright red cherries are naturally scattered on the mirror surface, some with thin green stems, loosely and irregularly distributed, the red fruits form a small visual rhythm around the face in the mirror. Warm soft light from the upper left front illuminates the real person's face, back of the hands, and the edge of the mirror frame, dark long hair and background are pressed into warm brown shadows, the mirror surface maintains low-brightness soft reflection, small areas of moist highlights appear on the cherry surfaces, warm brown, soft skin tone, old gold beige, and cherry red as main colors, 50 to 85mm close-up feel, soft focus, warm diffusion, low contrast, film grain, slight halation, slight bloom, vintage lens softness, soft highlight roll off, old movie, old magazine, vintage still life portrait texture, real face, face in the mirror, hands, mirror surface and cherries are unified and softened. Clearly readable Soran integrated into the antique mirror's carved frame near the person's hand, naturally curved along the curvature of the oval mirror frame in old silver or dark gold metal engraving; hidden Soran integrated into the frame's acanthus patterns, long hair strands, cherry stem directions, tabletop wood grain, mirror highlights; microscopic Soran composed of mirror frame wear points, cherry highlights, hair intersections, fine metal scratches, and stem nodes. Negative: Different person in the mirror, multiple faces, a third face, wrong reflection direction, misaligned mirrored facial features, hands not corresponding to reflection, mirror frame passing through face or hand, extra fingers, webbed fingers, too many cherries, cherries arranged neatly, modern frameless mirror, LED makeup mirror, figure looking up and staring directly at the camera, sweet smile, reflection in mirror too sharp, commercial studio shoot, overall orange-yellow filter too heavy, HDR, 8K ultra-sharp, plastic skin, commercial skin smoothing, external watermark, sticker logo, floating text, subtitles, unreadable Soran.

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

  • 抹胸

    16:9横屏,真实自然的日系清新室内摄影。一位25岁左右、身形娇小玲珑的成年中国女性,肩膀窄而圆润,手臂纤细,骨架小巧,身材比例自然匀称,胸围中等,腰部纤细但不夸张,整体散发甜美、温柔、俏皮的可爱气质,而不是成熟御姐或高挑时装模特风格。她拥有柔顺蓬松的银白色长直发,部分发丝从画面上沿自然垂落至肩部,几缕发丝被微风吹向画面左侧。人物穿着鲜亮草绿色无肩带短款抹胸上衣,真正作为日常外穿服装的tube top,横向平直上缘,宽幅连续的一体式弹力棉针织面料,完整覆盖胸部,贴合自然中等胸围,衣摆平整,绝不出现独立罩杯、钢圈、肩带或胸罩结构。抹胸表面具有深蓝黑色复古字母、横向条纹和略微褪色的印花。人物正面面

  • 黄昏

    A quiet unposed fine art photograph of a young East Asian woman curled sideways in a wicker chair by the window at dusk, caught in a private unguarded moment, not posing. Long wavy dark brown hair falling loose over one shoulder and across her face, slightly tousled. Her gaze is lowered and averted

  • 热血少年宝玉角色设定图

    以当前固定参考肖像作为预览人物槽,为角色名“宝玉”制作少年漫风格的虚构示意设定图。面部与发型依据参考中可见特征;服装、姿势、配色和类型化光效均为可编辑的创作默认值,不代表对用户个人资料或性格的了解。 Create a fictional illustrative shonen-style character sheet named “宝玉,” using the current fixed portrait as the preview-subject slot. Base face and hair only on visible reference features; costume, p

  • 黄昏藤椅

    A quiet unposed fine art photograph of a young East Asian woman curled sideways in a wicker chair by the window at dusk, caught in a private unguarded moment, not posing. Long wavy dark brown hair falling loose over one shoulder and across her face, slightly tousled. Her gaze is lowered and averted

  • 薰衣草墙花卉人像

    无需外部参考,生成成年女性越过薰衣草色墙垂双臂持大花束的3:4写实时尚画面。

  • 极简文字的个人色彩诊断图

    以固定参考肖像为对象,通过服装色彩样片进行图表优先的视觉比较,文字简短,不写段落。结果是基于可见肖像的造型建议,不宣称经过校准的科学诊断。 Use the configured portrait as the subject and compare clothing-color swatches in a diagram-first layout. Keep labels brief and omit paragraphs. Present the result as a visual styling suggestion based on the visible portrait, not