OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
黑色长裙内藏微缩发光城市人像
Portrait in a Black Gown Hiding a Miniature Glowing City
傍晚都市街头的单张超现实创意人像：成年亚洲女性展开黑色长裙，裙摆内部呈现一座温暖发光、具有街道与楼宇纵深的微缩夜城。
提示词 / Prompt
中文提示词
竖版3:4，单张创意人像图片，真实摄影质感与克制的超现实动画元素结合；不要拼贴、不要四宫格、不要信息图、不要文字。主体为一位22岁以上原创成年亚洲女性，站在傍晚都市街头，背对镜头后微微回头，身形修长，气质安静高级。她穿优雅黑色长裙，双手自然轻轻提起并展开裙摆；人物保持真实人像摄影质感，皮肤细腻自然，头发盘起或低扎，造型简洁高级。裙摆内部不是普通布料，而是一整座清晰可见的发光微缩夜城：街道、车流、楼宇、窗户灯光、十字路口与高楼之间的纵深层次都应明确呈现，仿佛繁华城市被装进裙子里。裙摆边缘保留真实布料的垂坠感，内部世界像独立的夜景宇宙，灯光温暖、细节丰富、层次分明。背景是真实但略微虚化的都市街道，冷色傍晚环境，远处路灯和散景光斑营造电影感。人物居中偏下，裙摆为视觉焦点，整体兼具时尚大片、高级梦幻与故事感。禁止卡通脸、低幼插画感、廉价特效、畸形手、多余人物、文字水印、夸张科幻机甲感、婚纱感和杂乱背景。
English prompt
Vertical 3:4, single creative portrait image combining realistic photographic texture with restrained surreal animation elements; no collage, no four-grid layout, no infographic, no text. The subject is an original adult Asian woman aged 22 or older, standing on an urban street at dusk, slightly looking back over her shoulder, tall and slender with a quiet, high-end temperament. She wears an elegant black long dress and naturally lifts and spreads its hem with both hands. Keep the person in realistic portrait-photography texture with delicate natural skin, hair in an updo or low ponytail, and a clean high-end look. The inside of the skirt is not ordinary fabric but an entire clearly visible glowing miniature night city: streets, traffic, buildings, window lights, intersections, and layered depth between high-rises must be distinct, as if a bustling city were packed into the dress. Preserve the drape of real fabric along the hem, while the interior becomes an independent night-scene universe with warm lights, rich detail, and clear layers. Use a real but slightly blurred urban street background in a cool dusk environment, with distant street lamps and bokeh spots for a cinematic feel. Place the subject slightly low and centered, making the skirt the visual focus. Combine fashion-editorial grandeur, high-end dreaminess, and narrative atmosphere. Prohibit a cartoon face, childish illustration feel, cheap effects, deformed hands, extra people, text watermarks, exaggerated sci-fi mecha styling, wedding-dress styling, and a messy background.
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
- 1girl
gpt image2.5生成
- 【超必杀】圣光白米大肥鱼
整体基调：东方史诗神话灾难大片质感，热血动漫爆发感融合好莱坞写实CG，UE5电影渲染，HDR光追，真实物理，强烈金色侧逆光，体积沙尘，电影景深，动态运动模糊，节奏干脆迅猛。 图1锁定角色：蓝渐变长卷发，头顶呆毛，鲸鲨鱼耳，鲸鲨长尾，女仆裙装，白色围裙，围裙印有小鲸鱼图案，Q版比例。 图2锁定巨型黑黄条纹甲壳虫王，巨口獠牙、尖刺前爪、虫群头领气质。 图3只用于冲击帧视觉语言【严格遵循Impact Frame规则】：冲击帧不是连续动画，不是撕裂米粒浪潮喷涌过程，也不是爆炸过程，而是**米粒旋风接触虫王躯干的命中顶点瞬间，强行打断正常运动、插入极短静态定格画面的视觉卡点**。冲击帧仅0.2秒，帧内无
- 法式风情地标美食海报
A premium, clean and elegant poster concept built from the source’s broad request. Eiffel Tower, Arc de Triomphe, ratatouille and Provençal bouillabaisse are curator-selected illustrative examples, not details stated by the source; they can be replaced in a future variant. The source example image i
- 梦回江户浮世绘古典人物像
A reference-led Edo-period ukiyo-e portrait transformation that preserves the supplied person’s facial identity while restyling hair, clothing and accessories in traditional Japanese fashion. The current ref-10a-v1 is the generic person preview for this workflow, not a claim about any external named
- 盛世长安万国来朝图
A text-driven historical reconstruction of the source scene: an aerial view of Kaiyuan-era Chang’an, Emperor Xuanzong and Yang Guifei looking out from Hanyuan Hall, and a distant tribute procession. The configured generic portrait is used only as a face-identity anchor for Yang Guifei in this genera
- 威震天高定西装时尚大片
A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面，保留银灰机甲、高定西装与赛博朋克霓虹场景；不声称复现某一改编版本的精确造型。