OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
冰棍里的微缩城市景观摄影
Miniature Cityscape Photography in a Popsicle
将城市目的地的地标与文化元素冻结在透明冰棍内部，制作4:5超写实旅行概念摄影；城市、地标和建筑为可编辑输入，手部仅作自然持棒动作。
提示词 / Prompt
中文提示词
使用以下可编辑默认值创作一张超写实的4:5竖版概念旅行摄影：城市/国家=日本京都；标志性地标=清水寺；当地建筑=传统町屋。将目的地精髓冻结在画面中央一根晶莹剔透的冰棍内部。冰层中构建清晰的微缩3D世界，以地标为主体，周围有可辨识的当地建筑、开花树木、小咖啡馆、街道家具和克制的文化细节。微缩世界必须像真实嵌入冰层并被冻结在时间中。 冰棍要呈现真实透明冰块、冻结气泡、细小裂纹、边缘霜、融化液滴、内部冷凝、微妙瑕疵、半透明深度以及物理准确的折射和反射。将冰棍置于同一城市真实且柔和虚化的街景前，在平凡现实与神奇冷冻微缩世界之间形成对比。一只自然的人手从底部握住木质冰棍棒，具有真实皮肤纹理、指纹和细小褶皱；手部只是产品互动，不需要固定身份。使用电影感旅行摄影与微距摄影、浅景深、柔和金色日光、轻微镜头压缩、美丽虚化、自然色彩和清楚的前后景纵深。冰棍与地标保持清晰居中，画面无文字。避免虚构地方事实或地标、通用旅游陈词滥调、不真实冰块、不可信尺度、畸形手部或手指、额外人物、过度HDR、CG塑料感、3D渲染感、Logo、文字、水印和无依据的分辨率承诺。
English prompt
Create a hyper-realistic 4:5 vertical conceptual travel photograph using these editable defaults: city/country = Kyoto, Japan; iconic landmark = Kiyomizu-dera; local architecture = traditional machiya. Freeze the essence of the destination inside a crystal-clear ice popsicle centered in the frame. Build a sharp miniature 3D world inside the ice with the landmark as hero, surrounded by recognizable local architecture, flowering trees, a small café, street furniture, and restrained cultural details. The miniature world must appear physically embedded and frozen in time. Make the popsicle realistic with clear ice, frozen bubbles, tiny cracks, edge frost, melting droplets, internal condensation, imperfections, translucent depth, and physically accurate refraction and reflections. Place it against a softly blurred real street scene of the same city, contrasting ordinary reality with the magical frozen miniature. A natural human hand enters from below holding the wooden stick, with realistic skin texture, fingerprints, and creases; the hand is only a supporting product interaction and does not require a fixed identity. Use cinematic travel and macro photography, shallow depth of field, soft golden daylight, subtle lens compression, beautiful bokeh, natural colors, and clean foreground-to-background depth. Keep the popsicle and landmark sharp, centered, and text-free. Avoid invented local facts or landmarks, generic travel clichés, artificial ice, implausible scale, distorted hand or fingers, extra people, HDR excess, CGI plasticity, 3D-rendered look, logos, text, watermarks, and unsupported resolution claims.
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。