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

京都纸上生长的3:4微缩城市旅行封面

A 3:4 Miniature City Travel Cover Growing on Kyoto Paper

一张3:4竖版旅行封面：京都城市街区从纸质地图自然生长为微缩模型，以清水寺为主地标、鸭川和棋盘式中心街区为辅助场景，强调真实方位关系、70%可辨认地理与30%几何简化、纸张与微缩模型材质、准确地名/坐标/短句排版。

京都纸上生长的3:4微缩城市旅行封面 — AI image creation
京都纸上生长的3:4微缩城市旅行封面

提示词 / Prompt

中文提示词

创作一张京都（英文名：Kyoto）的3:4竖版微缩城市旅行封面。 真实地理依据 按已核实的地点资料组织地图：京都中心街道呈棋盘式格局，鸭川流经市区。清水寺位于东山音羽山坡地，以木构清水舞台与桧皮葺屋顶为标志。主场景：清水寺坡地与舞台；辅助场景：鸭川沿岸日常步行、中心棋盘街区的商铺与自行车。保持这些地点的地图方位关系一致。。代表性城市参考坐标为35°00′42″N 135°46′05″E；它仅作为城市参考点，不代表测绘精度。保留上述河流、山坡和街区的空间关系，不虚构地理、建筑、地标或地方习俗。 主视觉 呈现一座经过艺术简化但仍可辨认的真实城市，约70%为清晰可读的地方地理与地标，30%为克制的几何抽象。城市从铺在桌面的干净纸质地图中连续生长：印刷道路逐渐成为立体街道，平面地形形成低矮起伏，建筑自然接触纸面。不出现独立底座、漂浮岛屿或模型被另行摆放的感觉。 以前景东山坡地上的清水寺、向外挑出的木构舞台与独特桧皮葺屋顶（英文默认值：Kiyomizu-dera on the eastern hillside, with its projecting wooden stage and distinctive cypress-bark roof）作为主要场景；加入鸭川沿岸日常步行与桥边小憩（英文默认值：an everyday walk and a small bridge-side pause along the Kamo River）和京都中心棋盘式街区中的小店与自行车生活场景（英文默认值：a small shopfront and bicycle activity within Kyoto's central street grid）两个较小辅助场景，并遵循地点资料中的真实方位关系。三个场景共呈现15–20个局部尺度统一、约1:87模型人偶质感的微缩人物。前景安排一位明确成年的主要游客，其身份绑定已配置的ref-10a-v1；所有人偶面部都保持微小、无细节，不画可识别的真人面孔。动作简单可读，脚接触地面、手与物件接触合理；画面拥挤时先减少次要人物。 构图与材质 采用高机位斜俯视，让地图布局、屋顶和建筑侧面同时可见，透视方向一致。主体城市模型位于中部至下部，约占三分之二空间；一个清楚的主要地标，两个辅助场景。左上留白放地点常用中文名，其下放通行英文名和代表性坐标；右下留白放沿鸭川慢慢走（英文默认值：A slow walk by the Kamo River）。文字和留白不得遮挡关键地理。 表现细腻纸纤维与轻微折痕；使用哑光树脂、细卡纸、微型木构、植绒草皮和模型树冠，水面仅有克制反射。采用柔和摄影棚侧光，阴影与反射方向一致。保留当地建筑与自然环境的色彩，不把画面机械压成灰色。整体呈真实微缩模型摄影观感，城市主体景深充足，只有纸张外围轻微虚化。避免卡通、低多边形、游戏场景及塑料玩具感。 文字与成品 只排版并各出现一次指定的四项文字：地点中文名、地点英文名、给定坐标字符串和给定日常短句。文字清晰可读；中文标题使用稳重克制的宋体风格，短句用自然小巧的手写风格。不要生成细小街名或其他文字。不要标志、口号、签名、徽章、边框或水印。这是AI生成的微缩风格作品，不冒充真实拍摄的实体沙盘。未另行核实前，不声称实际像素尺寸、独立文字图层编辑、图片检查、EXIF/GPS清理或其他后处理已完成。

English prompt

Create a single 3:4 vertical miniature-city travel-cover illustration for Kyoto (Chinese default: 京都). GEOGRAPHIC PROFILE Use this verified place profile as the factual layout reference: Kyoto's central streets form a grid and the Kamo River runs through the city. Kiyomizu-dera stands on the eastern hillside of Mt. Otowa, with its wooden stage and cypress-bark roof. Main scene: the temple slope and stage. Supporting scenes: an everyday walk beside the Kamo River and a central grid-street shop/bicycle scene. Keep their map positions coherent.. The representative city reference coordinate is 35°00′42″N 135°46′05″E. Treat it as a city reference point, not a claim of surveying accuracy. Preserve the described river, hillside and street-grid relationships; do not invent geography, architecture, landmarks or customs. CORE IMAGE Show an artistically simplified but recognizable real city, with about 70% legible local geography and landmarks and 30% restrained geometric abstraction. The city grows continuously from a clean paper map spread on a table: printed roads rise into three-dimensional streets, low terrain becomes gentle relief, and buildings sit naturally on the paper. No detached base, floating island or separately placed model. Use Kiyomizu-dera on the eastern hillside, with its projecting wooden stage and distinctive cypress-bark roof as the main foreground scene (Chinese default: 东山坡地上的清水寺、向外挑出的木构舞台与独特桧皮葺屋顶). Include an everyday walk and a small bridge-side pause along the Kamo River and a small shopfront and bicycle activity within Kyoto's central street grid as two smaller supporting scenes, preserving the location profile's real spatial relationships (Chinese defaults: 鸭川沿岸日常步行与桥边小憩; 京都中心棋盘式街区中的小店与自行车生活场景). Across all three scenes, show 15–20 miniature people at consistent 1:87 model scale. Give one clearly adult foreground traveler the configured identity reference ref-10a-v1; keep all miniature faces small and non-detailed, with no recognizable real faces. Use simple readable actions, feet grounded and hands in plausible contact; reduce secondary figures first if the image feels crowded. COMPOSITION AND MATERIALS Use a high-angle oblique top-down view so map layout, rooftops and building sides are visible with consistent perspective. Keep the main city model in the middle-to-lower two-thirds, with one clear focal landmark and two supporting scenes. Leave uncluttered space at upper left for the common Chinese place name and, beneath it, the standard English name and representative coordinates; reserve lower right for A slow walk by the Kamo River (Chinese default: 沿鸭川慢慢走). Do not let text or whitespace cover essential geography. Render fine paper fibers and slight map folds; matte resin, fine card, miniature wood structures, flocked turf and model-tree canopies; restrained water reflections. Use soft studio side light with consistent shadows and reflections. Keep local architectural and natural colors rather than turning everything grey. Aim for realistic miniature-model photography with sufficient depth of field over the city, and only slight blur at the outer paper edge. Avoid cartoon, low-poly, game-scene or plastic-toy appearance. TEXT AND FINISH Typeset only the four specified text elements once: Chinese place name, English place name, the supplied coordinate string and the supplied short everyday caption. Use clear readable type, restrained Song-style lettering for the Chinese title and a small natural handwritten style for the caption. Do not fabricate tiny street names or other text. No logo, slogan, signature, badge, border or watermark. This is an AI-generated miniature-style artwork, not a photograph of a physical model. Do not claim pixel dimensions, independent text-layer editing, image inspection, EXIF/GPS removal or other post-processing unless separately verified.

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

  • 超写实电影感大唐皇后

    超写实电影感静帧，1girl，唐代皇后，威仪端庄的年轻女子，高耸双环望仙髻，凤冠缀珠翠与红宝石，额贴花钿，齐胸绛红织金抹胸襦裙，外罩大袖纱衣，金约臂钏与璎珞垂胸，9:16 竖屏构图，人物居中全身站立，背后朱红立柱与殿门向画面深处层层递进形成纵向纵深，两侧仪仗队列虚化，大明宫正殿，MetaHuman 级皮肤质感，次表面散射，可见毛孔与细小绒毛，头发梳理整齐服帖，发丝根根分明、层次清晰，贴合头型，鬓角收拢，无翘起碎发与凌乱飘散，路径追踪全局光照，殿内天光与冷调侧光，物理材质，ACES 色调映射，50mm 镜头，浅景深，轻微胶片颗粒，8K，超精细，焦点锐利

  • 超写实电影感大唐美女

    超写实电影感静帧，1girl，唐代贵妃，丰腴雍容的年轻女子，高髻盘发插金步摇与珍珠，额间贴花钿，鬓边斜红，齐胸抹胸式石榴红暗花绫罗襦裙，肩颈与锁骨线条清晰，织金纹样与缂丝暗纹细致可见，披帛缠绕臂间自然垂落，9:16 竖屏构图，人物居中偏上，头顶留少量空间，下方完整呈现披帛垂落与裙裾，沉香亭内，身后牡丹与半透轻纱帷幔纵向延伸，MetaHuman 级皮肤质感，次表面散射，可见毛孔与细小绒毛，头发梳理整齐服帖，发丝根根分明、层次清晰，贴合头型，鬓角收拢，无翘起碎发与凌乱飘散，路径追踪全局光照，烛火暖金侧逆光，物理材质，ACES 色调映射，85mm 镜头，浅景深，轻微胶片颗粒，8K，超精细，焦点锐利

  • hyperrealistic cinematic girl

    hyperrealistic cinematic still, 1girl, cosplay, [character: hair + costume + prop], intricate costume in real fabric, leather and metal hardware, [location], MetaHuman-grade skin with subsurface scattering, visible pores and vellus hair, individual hair strands, path-traced global illumination, phys

  • cos girl

    生成一张竖屏电影感角色人像：一位年轻亚洲女性 coser，扮演[角色]，全身/七分身站在画面中央，纵向构图，背景是[场景]的局部，只保留肩后的环境氛围。她穿着细节丰富的 cosplay 服装，面料有真实的织物纹理、缝线与金属扣件，配有[道具]。皮肤是真实人像质感，可见毛孔、细小绒毛和次表面散射的通透感。头发为[发色]的[发型]，梳理得整齐服帖，发丝顺滑有光泽、根根分明、层次清晰，贴合头型与脸颊，鬓角自然收到耳后，发梢干净利落，没有翘起的碎发、没有凌乱飘散，也不遮挡面部。镜头 85mm、f/1.8，浅景深，背景柔和虚化，光线为柔和侧逆光加轮廓光，画面带轻微胶片颗粒，8K 超精细，整体为电影静帧质

  • 机能girl

    cosplay 摄影，年轻亚洲女性，银白色短波波头，黑色机能风外套带蓝色发光电路纹，露指手套，夜晚霓虹街道，地面雨水反光，蓝紫色轮廓光，真实皮肤质感，85mm 镜头，电影感，超精细

  • cosplay 摄影写真

    cosplay 摄影写真，一位年轻亚洲女性，黑色长发配银质发簪，白色与浅蓝渐变的刺绣汉服，宽袖，手持细长长剑，雪山背景，空中飘雪，电影感柔和轮廓光，真实皮肤质感，浅景深，85mm 镜头，超精细，8K