Isometric için Görsel promptları

2x2 grid, 16:9, do this for 4 {argument name="topic" default="extreme sports"}: <isometric_diorama_topology> [ AI_INFER: ROOFING / AWNINGS ] / /| / [ W ] [ O ] [ R ] [ D ] / | <-- Text forms the back wall. / (AI_INFER: Shelves/Props)/ | Materials match [TOPIC]. +-----------------------------+ | | | | | [ AI_INFER: Mini ] | + | [ Character Pose ] | / | | / +-----------------------------+/ [ AI_INFER: Themed Floor Base ] </isometric_diorama_topology> INSTRUCTION: 1. Render as a photorealistic, physical scale model on a desk. 2. The letters of [WORD] must be thick, architectural blocks. 3. Warm, cozy lighting glows from inside the structure.

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体身份、结构、姿态、真实质感、自然光影和原有色彩氛围，仅进行轻微高级调色，使其具有艺术杂志、独立出版物与展览图像质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片主体最具识别度的**轮廓、结构、姿态与叙事关系**，重构为一组 **3D miniature architectural landscape** 风格的极简艺术画面：以 **isometric view / cut cube composition / perspective of an underwater continental shelf** 的方式呈现，主体像一个被剖开的微缩立体场景，具有正确的等距视图与清晰空间层级。整体以**微缩灯塔景观**为核心语义，可根据原图主体特征灵活转译，但必须保留一眼可辨的识别性与原始叙事关系。 下半部分不是写实插画，而是将主体压缩为**简洁几何形状、扁平色块、细线条与留白**的抽象化表达；在极简基础上保留适度丰富的结构细节，使画面兼具建筑图解感与艺术海报感。主体应像一件置于白色纹理纸上的微型立体模型，带有 **hand-drawn architectural illustration** 气质：线条精细、层次清楚、细节克制而准确，避免厚重真实渲染。 画面中加入明确的**脚手架逻辑**，参考你提供的图像：脚手架不是随意装饰，而应作为包裹、支撑、搭建或介入主体结构的理性系统，与主体共同形成空间秩序。脚手架可由细密的水平、垂直构件与局部连接节点组成，围绕主体外轮廓、关键转折或立体切面展开，呈现一种“正在被建构、修复、测绘或展示”的感觉；视图必须准确，透视关系清晰，不要画成漂浮拼贴。 构图保持**主体居中、画面平衡、秩序克制**，并通过少量水平线、纵向构图线、环形元素或剖面边界增强空间感。背景使用**白色纹理纸或极浅米白纸面**，干净、安静、无阴影或仅有极弱的结构层次，不要厚重投影。保留大面积留白，让主体像悬浮于展览图录或建筑研究海报的版面中。 配色从上方照片中提取灵感，但需重新处理为**更明艳、清透、治愈且有生命力**的高级色系，而不是直接照搬原始色值。保留原图的色相线索后，适度提亮、提纯、去灰，使颜色更鲜活、更轻盈；可形成清澈蓝、湖水青、嫩绿、明黄、珊瑚橙、桃粉、淡紫等柔和而明快的综合色关系，通过冷暖对比与明度节奏建立精致层次。避免灰脏、暗沉、发旧、莫兰迪化、廉价糖果色和塑料感。 文字可少量介入，加入简洁的英文标题、编号或年份，并与主体、脚手架或留白形成自然的排版关系。文字应精致、现代、克制，像国际设计工作室、建筑海报、艺术展览海报和高端品牌视觉系统中的编辑性标注，不喧宾夺主。 整体风格呈现**高级、现代、雅致、克制、艺术化**的视觉效果，融合微缩立体景观、建筑剖面图、等距视图、脚手架系统与极简海报版式。避免过度滤镜、廉价塑料质感、卡通感、强电脑生成感、模板化效果、错误视图和无逻辑的装饰性结构。

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，延续上下双层逻辑：上半部分为真实摄影，下半部分为对原图核心意象的几何化重构，上下形成现实与记忆之间的呼应。 上半部分保留原始照片，保持主体身份、结构、姿态、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物与展览摄影质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的**主体、轮郭、姿态与叙事关系**，进一步判断原图真正成立的核心主题、视觉隐喻或审美关系，只保留这一层最值得被记住的信息重新创作。不要完整复刻场景，不追求写实描摹，也不要把所有物体逐一转换成插画；主动删除无关环境与细碎信息，只留下一个核心主体及极少数真正参与叙事的关系。 样式逻辑采用**{argument name="重构样式" default="几何构成 + 智能马赛克重组"}**。将主体与空间压缩为清晰的几何块面、矩形单元、细线框架与层叠网格，用模块化、建筑化、像素化但经过设计整理的方式重构画面。不是随机像素化，而是根据主体结构智能归纳：大形体保持明确轮廓，小细节被转译成有秩序的色块、格点、切片、台阶状边缘与局部拼接关系，使画面既有马赛克般的理性分解感，又仍然一眼可辨原始主题。可适度加入局部轴线、对齐线、边界框、留白分区和少量装饰性几何细节，形成高级编辑设计与建筑图解感。 下半部分以**极度浅色背景和大面积留白**作为主要空间。背景色不固定，根据原图综合色温与情绪智能匹配为接近白色的极浅综合色，可微暖、微冷或带极轻微色相，但必须轻、净、安静。空白本身承担空气、距离和呼吸感，让几何主体更突出。 构图强调**视觉重心、比例关系、负空间、模块节奏、对齐秩序与不完全对称**。主体可偏置、悬置、落在低重心区域，或由多个几何层级向中心聚合；若原图最动人的地方是一种关系——例如人与建筑的尺度、物与环境的并置、局部结构之间的呼应——应优先保留这种关系，并用几何分块和马赛克结构加以强化，而不是平均铺满画面。 配色保持你当前喜欢的逻辑：从原图提炼综合色温和最具有生命力的颜色，再转译成一种**{argument name="色盘风格" default="温暖、明快、略带稚拙感的艺术家色盘"}**。整体以奶油黄、杏色、粉橘、珊瑚粉、旧玫瑰等温暖色块，与天空蓝、浅青绿、薄荷绿、灰绿等清凉色形成松弛的冷暖碰撞；允许极少量砖红、橙红、深绿、土褐或黑色作为视觉锚点。颜色不必完全服从真实物体，可根据画面节奏进行局部换色、错色和跳色，但必须保持整体和谐。色块应平涂、干净、克制，避免脏灰、统一滤镜感和高饱和数字色。 文字不预设固定标题、地点、编号或语种，根据原图的主题、动作、环境、情绪或隐喻自由生成极少量真正有意义的文字。文字可作为版式系统的一部分，置于留白区、底部中心、边角或几何分区之间，使用细瘦、克制、疏朗的排版方式，与几何结构形成呼应；整体保持小、轻、安静，不机械套模板。 整体气质应像**建筑图解、艺术地图、现代拼贴海报与高级编辑设计**之间的结合：安静、理性、精致、现代，同时保留记忆化提炼与色彩温度。避免完整场景复刻、随机像素化、贴纸逻辑、繁复纹理、光滑3D、卡通模板感和为了丰富而加入无意义元素。

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体结构、空间关系、真实材质、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物与展览摄影质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的**主体、轮廓、姿态与叙事关系**，按照“解构—筛选—提炼—重构”的逻辑，转化为具有 **3D / isometric 空间感的治愈系积木雕塑**。重点保留主体最独特的体量比例、轴线、曲线、穿插、层叠、遮挡与负空间，以圆润、简洁、具有触感的模块化体块重新组织；不完整复刻细节，但必须一眼感受到与上方原图的对应。 构图根据主体自身的视觉重心、姿态方向和空间关系自适应设计，通过大小体块、高低错层、前后穿插、局部悬浮、疏密变化与大面积留白建立节奏。积木可以拼接、叠放、嵌套、穿越或自然错位，使主体既保留身份，又具有当代艺术玩具般的雕塑感和轻松想象力，避免机械拆件和简单像素化。 **配色必须从上方原图本身分析产生。** 先识别照片中最有生命力、最有辨识度的主色关系，以及综合色温、明度层级、冷暖呼应和关键点色，再将这些颜色重新调制为更柔和、清澈、明亮、有空气感的治愈色彩体系。保留原图的色相身份与情绪记忆，但适度提高明度、降低刺眼对比、净化灰脏杂色，使颜色呈现温柔、童趣、轻盈而高级的感觉。不同照片应自然得到不同配色，不固定使用任何预设色卡，也不要为了“治愈感”强行加入原图不存在的颜色。 色彩通过**主色面积、辅助色层次、同源深浅与极少量鲜活点色**建立节奏，让主体看起来丰富但不杂乱、可爱但不甜腻、柔和但有精气神。积木材质采用细腻哑光、柔和漫反射的质感，带轻微纸浆、木质、粉蜡或柔性材料般的触感，边角圆润、阴影轻柔，避免塑料高光、金属感、厚重CG和廉价玩具质感。 文字建立轻盈的高级编辑式微排版系统，从照片的光影、动作、空间、情绪或象征意义中提炼一个2–5词的标题，并搭配少量状态词、地点、编号、方向词或微型注释，不使用年份。文字可沿积木边缘、模块缝隙、视觉轴线或负空间排列，也可与体块形成穿插、遮挡与对齐，让文字自然成为积木构图的一部分。 整体呈现 **真实摄影 × 治愈积木 × isometric空间 × 原图色彩转译 × 高级编辑设计** 的视觉气质，温柔、轻盈、童趣、安静、精致、有想象力但不幼稚。无论主体是人物、动物、植物、建筑、器物、食物、交通工具或自然景观，都应从原图自身的结构与色彩中发展出独特的积木组合和配色方式，避免固定色卡、乐高式复制、儿童卡通、电商玩具展示感和模板感。

Create a clean editorial poster featuring an isometric 3D country diorama of {argument name="country name" default="France"} floating on an off-white studio background. The landmass is shaped accurately like metropolitan France, with a separate small island for Corsica at the lower right, rendered as a thick carved terrain slice with vertical rocky cliff edges and soft cast shadows. Fill the map with lush green countryside, patchwork yellow and tan farm fields, forests, winding blue rivers, thin roads, tiny towns, harbors, boats, and regional landmarks. Place Paris near the center with a prominent miniature Eiffel Tower as the focal point, plus recognizable French scenery including snowy Alpine mountains along the southeast, Pyrenees-style snowy mountains along the southwest, Mediterranean coastline and marina at the bottom, Atlantic coastline with lighthouses and small sailboats at the left, and cathedral/castle-like landmarks scattered across the map. Use highly detailed miniature model realism, isometric perspective from above, warm daylight, crisp depth, realistic terrain textures, and a polished travel-atlas aesthetic. At the top, add centered typography: small spaced uppercase text "EUROPE", then a very large bold condensed uppercase title "{argument name="country title" default="FRANCE"}" in dark charcoal, followed immediately on the right by a vertical tricolor flag with three equal stripes blue, white, and red. Beneath the title, add small spaced uppercase metadata reading "{argument name="capital and population" default="PARIS • 67.4 MILLION"}". Keep the composition symmetrical, premium, uncluttered, with no extra labels, no border, no watermark, and no additional text.

Goal: Create a highly detailed isometric city diorama poster of {argument name="city name" default="Barcelona"}, Spain, presented as a miniature architectural model on a square wooden-edged base. Canvas: Vertical poster composition, 4:5 aspect ratio, clean off-white background with generous blank space above the diorama. Center the city model in a three-quarter isometric view, with the coastline and harbor along the front edge and the dense urban grid receding toward the top. Title text: At the top center, use small spaced uppercase text “CATALUNYA”, below it a very large tall condensed uppercase headline “{argument name="headline text" default="BARCELONA"}”, and below that small spaced uppercase text “SPAIN”. Use dark charcoal lettering, elegant travel-poster typography. City layout: Build a precise miniature version of Barcelona with a dense Eixample-style grid of square city blocks, orange terracotta rooftops, pale stone buildings, tree-lined avenues, small intersections, plazas, and tiny vehicles. The city should look like a premium museum-scale diorama with realistic lighting, crisp detail, and subtle depth of field. Visible landmark count: Include exactly 6 major recognizable landmark zones: 1) the Sagrada Família as a tall ornate basilica with many spires near the center, 2) a large green park zone resembling Parc de la Ciutadella on the upper left, 3) a rounded blue-and-red football stadium on the right side, 4) a bullet-shaped glass skyscraper resembling Torre Glòries on the left, 5) a tall sail-shaped waterfront hotel tower on a small peninsula near the front center-left, and 6) a beachfront and marina district along the front and right edge. Waterfront details: Show deep turquoise Mediterranean water wrapping the front edge of the square base, with a harbor, piers, docks, a marina filled with rows of small white boats, a sandy beach curving along the right side, and a few tiny sailboats and motorboats in the water. Add promenades, palm trees, roads, cranes, and small waterfront buildings. Style: Ultra-detailed 3D isometric diorama, realistic miniature photography, warm daylight, crisp shadows, saturated but natural colors, terracotta roofs, green parks, blue sea, and polished architectural model craftsmanship. The base should have a visible dark wood side edge, making the city feel like a physical tabletop model. Constraints: No people in close-up, no extra labels on the map, no watermark, no border. Keep all text clean and legible, and do not add additional cities or unrelated landmarks.

为这个 {argument name="location" default="客厅"} 提供 {argument name="number of ideas" default="5"} 个布局方案。为每个方案输出一张具有不同变化的图像。

2x2 grid, 16:9, do this for 4 tourist cities: input = [{argument name="location" default="city"} + {argument name="infrastructure type" default="infrastructure system"} + environment + {argument name="style" default="optional style"}] run infrastructural_typography_extraction: text_content := parse word_or_place word_identity := infer whether text is a city, brand, concept, landmark, district, event, or fictional place font_personality := infer heavy, elegant, brutalist, futuristic, coastal, industrial, organic, luxury, playful, or monumental letter style infrastructure_dna := infer visual grammar of infrastructure_system network_behavior := infer flow, looping, branching, stacking, crossing, tunneling, ramping, glowing, routing, or circulation logic letter_mapping := map infrastructure onto each glyph’s stems, bowls, counters, diagonals, curves, crossbars, and terminals material_system := infer realistic construction materials light_system := infer city lights, traffic trails, signage glow, window grids, reflections, or ambient illumination environment_logic := infer surrounding urban/landscape context scale_anchors := infer vehicles, people, trees, buildings, waterways, or transit elements camera := infer cinematic aerial, street-level, drone, tilt-shift, or architectural visualization view render: a readable monumental word built from the inferred infrastructure system. constraints: - no fixed city - no fixed road system - no copied composition - no random transport spaghetti - infrastructure must physically construct the typography - word remains readable at thumbnail scale

Goal: Create a clean browser-page screenshot showing a Chinese case-study section that presents a large bilingual infographic poster about an urban systems map. Canvas: Landscape screenshot, about 917×833 px, white webpage background, cropped so the very top shows the tail end of a Chinese paragraph and the bottom cuts off part of the poster. Use crisp UI-like rendering, not a full browser chrome. Webpage layout: At the top-left of the visible section, show a small framed picture emoji/icon followed by the bold Chinese heading “精选案例”, with a thin gray horizontal divider line underneath spanning most of the width. Below it, show a bold subsection title: “案例一：信息图可视化”. Under that title place one large infographic image centered with narrow margins. Main poster: Design an information-dense bilingual atlas poster titled “{argument name="main title" default="城市生命系统图谱"}” with the English subtitle “{argument name="English subtitle" default="Urban Metabolism Atlas"}”. Under the title add the small bilingual tagline “城市是一個有生命的系統 / The City is a Living System”. The poster should look like a professional architectural/urban-planning infographic: off-white background, navy headline text, thin gray panel borders, small bilingual labels, diagrammatic icons, and an isometric cutaway city illustration occupying the central majority. Poster top elements: On the upper left, include a compass rose marked N and a scale bar labeled “Scale” with tick marks 0, 50, 100, 200, 500m. Near the top center, include a boxed “System Legend” with exactly 10 colored line samples labeled: Electricity, Gas, Heating, Communication, Traffic, Logistics, Data Flow, People Flow, Clean Water, Wastewater. On the upper right, include one small inset map card labeled “Location”, showing a simplified city map with green parks, blue waterways, gray streets, and a red boundary. Central city illustration: Show a dense isometric smart city with many high-rise towers, mid-rise blocks, roads with cars and buses, a blue canal or river, bridges, street trees, plazas, underground metro tunnels and utility pipes visible in a cutaway at the bottom. Include small details such as a drone, airplane, rooftop solar panels, transit stations, pedestrians, and service vehicles. Use thin colored network lines running through the city to imply water, energy, data, logistics, and transit flows. Add exactly 5 visible circular numbered callout markers in the central scene: 6 on a building, 3 near a road/transport corridor, 8 near the right street edge, 9 in a green plaza, and 10 near an underground tunnel/canal edge. Side information cards: Place exactly 6 visible rounded rectangular system cards around the city, each with a colored numbered badge, bilingual title, small bullet labels, and mini diagrams. Left column has 3 cards: 1 “能源系统 / Energy Grid” with solar panels, battery storage, EV charging, and a car; 2 “城市水循环 / Water Cycle” with water plant, rainwater collection, sewage treatment, reclaimed water, and groundwater diagrams; 3 “交通网络 / Transportation” with a subway train, bus, roads, bicycle icon, and route lines. Right column has 3 cards: 6 “建筑内部系统 / Building Systems” with a cutaway building showing floors, HVAC, fire safety, BMS control, and pipes; 7 “公共服务 / Public Services” with hospital, school, fire station, police station, and community service icons; 8 “食物与物流 / Food & Logistics” with warehouse, cold chain, last-mile delivery, truck, boxes, and robot delivery. Keep the lower portions of the left and right columns slightly cropped by the screenshot edge, matching a captured page view. Visual style: Highly detailed semi-realistic isometric illustration mixed with technical infographic design, muted grays and whites with navy typography, accent colors yellow, cyan, red, purple, orange, and green. Text should be mostly legible at headline level but many small labels can be tiny. Maintain the feeling of an authentic Chinese web article showcasing an example image. Constraints: Do not add browser address bars, watermarks, floating toolbars, or extra social-media UI. Preserve the Chinese headings on the webpage and the bilingual poster title hierarchy. The image should look like a screenshot of a generated infographic embedded in a documentation page.

Goal: Create an ultra-detailed photorealistic isometric miniature scale-model diorama map of the world from {argument name="TV show" default="Game of Thrones"}, floating on a pure warm off-white studio background with a soft drop shadow beneath. Canvas: Vertical poster composition, 4:5 aspect ratio, centered diorama occupying the lower two-thirds and large title typography in the upper third. Use clean studio lighting, realistic shadows, shallow but readable depth, and a premium collectible tabletop model look. Title text: At the top, set small spaced uppercase text reading {argument name="world label" default="WESTEROS & ESSOS"}. Below it, place a huge tall condensed serif/fantasy title reading {argument name="main title" default="GAME OF THRONES"}, dark charcoal with slightly weathered texture; make the O in THRONES resemble the Iron Throne vertical blade motif. Beneath the main title, add small spaced text reading {argument name="subtitle" default="HBO | 2011"}. Map layout: Build two separate raised landmass miniatures divided by blue sea. On the left is Westeros, tall and narrow, with a snowy northern region at the top, a wall-like icy boundary, rugged green central lands, winding pale roads, mountain ridges, forests, lakes, castle miniatures, and a warmer southern desert region at the bottom. On the right is Essos, wider and more horizontal, with jagged central mountains, dry yellow-orange plains to the east, green-brown western terrain, rivers, roads, fortified cities, pyramids, towers, and ruins. Both continents have thick carved cliff edges like cutaway terrain, rocky brown sides, and tiny coastal islands. Discrete elements to include: Use exactly 10 heraldic banner markers placed across the map: 6 on Westeros and 4 on Essos. Westeros banners: one black northern banner in the snowy top region, one yellow-and-blue banner in the upper central region, one red lion banner in the central region, one dark red banner near the central-west castle, one blue banner in the lower central region, and one red lion banner at the southern castle. Essos banners: one dark blue banner in the mountain region, one red banner in the far upper-right city, one green banner at the right-side city, and one blue-gold banner in the lower central city. Add exactly 24 tiny sailing ships and boats scattered in the surrounding seas and between the continents, all miniature scale and varied in size. Visual style: Hyper-real miniature realism, isometric three-quarter top-down view, highly detailed terrain texture, tiny castles and settlements, crisp roads and rivers, muted fantasy-map colors, blue water, snow white north, ochre desert, mossy greens, rocky grays, and subtle atmospheric shadows. The diorama should feel like a handcrafted museum-quality prop or board-game map, not a flat illustration. Constraints: No people, no modern objects, no watermark, no UI, no border frame. Keep all text legible and centered. The background must remain plain off-white with ample negative space around the title and floating map.

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体结构、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物和展览摄影质感。为适配画幅，可自然扩展天空、地面或环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的**主体、轮廓、姿态与叙事关系**，重构为精致的极简等距视角插画，如一件陈列在纸面上的微缩立体模型或建筑沙盘。不要机械复刻照片细节，而是以概括体块、清晰边缘、简洁层级和微型场景关系重新表达主体，使其保留一眼可辨的身份特征，同时具有安静、克制、诗意的编辑插画气质。 整体采用**等距视角、微缩景观、纸面模型感**的构图逻辑：主体像被切割并安放在一小块纸面或微型基座上，周围保留大面积留白，通过体量对比、边缘裁切、轻微投影和少量微小细节建立尺度感与孤独感。可加入极少量辅助元素承托主体，但不得形成第二视觉中心。 配色完全从上方原始照片中提取，优先保留最具辨识度、最有气质和最能代表主体的颜色，再将复杂色彩**归纳、提纯、柔化并统一为有限色盘**。保留原图的冷暖关系与色彩性格，但降低杂色和视觉噪声，使颜色更平静、克制、柔和、有纸上编辑插画感；通过同色深浅、邻近色关系和少量色差区分体块，不凭空加入与原图无关的固定色系。使用精细墨线、扁平色面、轻微阴影和纸张颗粒表现结构与层次。 文字作为构图的一部分巧妙介入，从照片的主题、地点、动作、状态或情绪中提炼一个{argument name="英文标题" default="简短英文标题"}，并搭配极少量编号、短句或微型注释。文字保持细瘦、克制、现代编辑感，可沿留白边缘、主体基座、水平轴线或等距结构排列，与图形共同形成安静而精致的版式节奏。 整体参考**极简等距插画、微缩立体模型、纸上景观和高级编辑设计**，呈现安静、诗意、克制、精致、具有收藏感的视觉气质。避免卡通感、高饱和撞色、与原图无关的固定配色、塑料3D感、复杂场景堆积、电商感和模板感。

Function DrawArchitecture(input building/architect) Input Variable: {argument name="building or architect" default="Fallingwater"} Generate a hyper-realistic, 1:1 product photo of a "Blueprint-to-Model Desk Diorama" (Isometric miniature). 1. Semantic Extraction: - Identify style (brutalist, modernist, gothic), key forms, and one signature feature (cantilever, arch, atrium). - Figure: Chibi “architect” avatar holding a tiny scale ruler. - Finish: Matte PVC. 2. Container (Drafting Corner Box): - Structure: U-shaped cardboard drafting station (two walls + floor), desktop scale. - Props: tiny triangle ruler, pencil, scale bar. 3. Background (Blueprint Walls): - Walls: B&W blueprint lines, elevation drawings, annotations (original, inspired). - Floor: Blueprint fragments “explode” upward into paper folds. 4. Integration: - A 2D blueprint line rises into a 3D model piece (a wall or arch popping out) that the figure points at. 5. Visual Syntax: - Palette: Strict B&W blueprint world; full color figure + one accent prop. - Lighting: soft product photo, crisp details. - Label: "[Subject] — [Style/Architect]" Return: ONE image, 1:1, museum-miniature realism. <instructions> Input: building/architect Analyze style, era, signature geometry. Find 4 MUCH lesser-known buildings/architects in same lineage. Output: a 2x2 grid, each panel is DrawArchitecture for a lesser-known recommendation. </instructions>

Using REFERENCE_0 as the architectural source, transform the engraved scene into a realistic handcrafted 3D miniature diorama / scale model. Keep the same ancient temple, terraced hillside, stone retaining walls, stairways, trees, and tiny human figures, but convert everything from flat illustration into physical model materials with depth, shadows, and tactile detail. Present it from an elevated three-quarter isometric view on a clean light studio background. Add a polished dark wooden display plinth underneath the whole terrain and attach exactly 1 brass nameplate centered on the front edge reading {argument name="plaque text" default="The Temple of Artemis"}. Make the terrain look like a museum-quality architectural maquette: carved stone blocks, rocky cliff texture, miniature shrubs and cypress trees, weathered ivory temple columns, and subtle natural colors. Preserve the overall layout from the reference while making it feel like a tangible collectible model, not a drawing or painting.

Create a premium cinematic travel poster featuring an ultra-detailed photorealistic isometric miniature diorama of {argument name="destination" default="Santorini"}, {argument name="country" default="Greece"}. The canvas is vertical 4:5 with a clean warm off-white studio background and generous empty space at the top for typography. Center the scene as a floating collectible-scale island sculpture with steep dark volcanic cliffs, a circular caldera bay of deep blue water, and a soft natural shadow underneath. Build the miniature with dense whitewashed Cycladic houses stacked along the cliffs, narrow stairways, winding paths, terraces, small courtyards, flowering bougainvillea, beige stone walls, and bright cobalt-blue accents. Include exactly 6 prominent blue-domed churches, exactly 3 traditional windmills, and exactly 8 visible boats: 4 sailboats spread across the bay, 1 small motorboat in open water, and 3 small boats near the harbor. The water should be realistic with subtle ripples, turquoise shallows near the harbor, and darker navy tones in the center. Use warm late-afternoon Mediterranean sunlight, crisp shadows, high depth of detail, realistic miniature scale, and a polished luxury travel-advertisement finish. Typography: at the top, set a large elegant high-contrast serif title reading {argument name="headline text" default="SANTORINI"} in dark navy with wide letter spacing; beneath it, smaller spaced uppercase text reading {argument name="subheadline text" default="GREECE"}; below that, a thin gold divider line with a small centered diamond; then a tiny uppercase caption reading {argument name="caption text" default="AEGEAN ISLAND DIORAMA • 2026"}. Keep the composition clean, symmetrical, refined, and poster-ready, with no people, no logos, no watermark, and no extra text.

Goal: Create an ultra-detailed photorealistic isometric miniature scale-model diorama poster of the world from {argument name="anime title" default="Attack on Titan"}, presented like a collectible museum map on a clean off-white studio background. Canvas: Vertical 4:5 poster composition. The upper third is typography, the lower two-thirds is a floating square-cut terrain diorama with rugged rocky sides and a soft realistic shadow beneath. Top typography: Centered at the top, use tall condensed bold distressed sans-serif lettering. Small spaced text above reads "THE WORLD OF". Main title reads "{argument name="main title text" default="ATTACK ON TITAN"}" in very large dark charcoal letters. Small spaced text below reads "{argument name="studio line" default="WIT STUDIO • 2013"}". Diorama layout: Show the walled civilization as a high-angle isometric model with three enormous concentric circular stone walls and fortified gates. The center contains a dense circular royal city with radial streets and a white central monument. Surrounding rings contain miniature villages, farms, roads, rivers, forests, watchtowers, and tiny human figures. Beyond the walls at the back are snow-capped mountains, wilderness, scattered ruins, and open terrain. The outer edge of the model is a thick cliff-like cutaway rock base with grass on top. Labeled signs: Include exactly 14 small dark rectangular map-label plaques with white uppercase text, placed around the diorama: 1) "BEYOND THE WALLS" near the mountains, 2) "ZIGANSHINA DISTRICT" on the upper-left wall area, 3) "KROLVA DISTRICT" on the upper-right wall area, 4) "SHIGANSHINA DISTRICT" on the far right, 5) "LAKE NALLE" by a blue lake on the left, 6) "YARCKEL DISTRICT" on the left outer area, 7) "CHLORBA DISTRICT" on the lower-left area, 8) "HUMANITY'S STRONGEST" beside a small military crest on the lower-left, 9) "TROST DISTRICT" on the right outer area, 10) "TRAINING GROUNDS" on the lower-right, 11) "ROYAL CAPITAL MITRAS" at the central city, 12) "INNER WALL WALL SINA" on the innermost wall, 13) "MIDDLE WALL WALL ROSE" on the middle wall, 14) "OUTER WALL WALL MARIA" on the front outer wall. Subject details: Make the wall rings tall, pale stone, weathered, and segmented with massive gates and red-roofed towers. Populate the landscape with tiny soldiers, civilians, horses, tiled-roof houses, roads, farmland plots, bridges, streams, and forests. Add a few tiny Titan-like humanoid silhouettes outside and near the walls for scale, but keep the scene map-like rather than action-focused. Visual style: Hyper-realistic miniature model photography mixed with anime-world cartography, crisp isometric perspective, warm daylight, realistic shadows, high texture detail, tiny hand-painted model figures, natural greens and browns, pale stone walls, snowy gray mountains, cinematic depth of field but all important labels legible. Constraints: Keep the image as a single poster, no border, no watermark, no extra logos. Preserve the exact 14 map labels listed above and the three wall labels. Use an off-white background and a centered floating diorama with clean studio lighting.

Ultra-detailed photorealistic isometric miniature scale-model diorama shaped exactly like the official crest outline of {argument name="club name" default="[CLUB NAME]"} — not a square tile, but the true precise silhouette of the badge, extruded downward into a thick slab with rough natural cliff-like edges, like the crest physically cut out and lifted. The slab follows every curve, point and detail of the real crest shape precisely. The entire top surface is a richly detailed miniature landscape rendered exclusively in club's official club colors — {argument name="primary color" default="[PRIMARY COLOR]"} and {argument name="secondary color" default="[SECONDARY COLOR]"}. Every surface, building, road, tree, field and terrain feature is tinted and colored strictly within this palette. No realistic natural colors — everything is remapped to the club's colors. The terrain still has full physical detail: elevation changes, tiny buildings, roads, trees, plazas, micro-detail throughout — but all of it exists only in the club color palette, creating a dreamlike monochromatic world in those colors. Style: hyper-realistic tilt-shift miniature photography — extremely sharp, everything in focus, no blur. Soft warm studio lighting from above, gentle diffuse shadows. The color palette is strict and unwavering — PRIMARY COLOR dominates, SECONDARY COLOR as accent throughout. Layout: the crest-shaped diorama floats centered in the lower two-thirds of the frame on a pure off-white studio background with a soft drop shadow beneath, clear margins on all sides. Upper third is empty off-white space with minimalist editorial typography, centered: small wide-tracked caps with the league name at the very top, then [CLUB NAME] in a bold condensed sans-serif in medium charcoal grey — large and dominant — with a small flat rectangular flag of [COUNTRY] sitting immediately to the right of the club name, vertically centered, sized to the cap-height of the club name. Then small wide-tracked caps below with founded year and home city. Minimalist editorial poster aesthetic, premium print quality, 4:5 aspect ratio.

Goal: Create a polished editorial SaaS product exploration image for an AI agent collaboration platform called {argument name="product name" default="AgentBoard"}, showing two large web UI screens side by side on a warm off-white background: a marketing landing page on the left and the product dashboard on the right. Use refined startup design, soft shadows, rounded cards, thin gray dividers, lots of whitespace, muted forest-green accents, black serif display typography for the landing headline, and small clean sans-serif UI text. Canvas: Wide 4:3 composition, approximately 1200×900. Place two tall browser-like panels with rounded corners and subtle drop shadows, separated by a narrow gutter. Background is light cream with faint grain and very soft vignette. Left screen, marketing landing page: Top navigation bar with the logo text “AgentBoard” at top left, 4 centered nav links labeled Product, Solutions, Resources, Pricing, then Log in and a dark green “Start for free” button on the right. Hero area has a small pill label “AI-NATIVE WORKSPACE”, a large three-line headline reading “One board. Many agents. Real outcomes.” with “Real outcomes.” italic and green, supporting line “Plan, build, and ship work—together.”, and 2 CTA buttons: dark green “Start for free” and light outlined “Book a demo”. To the right of the hero text, show an isometric workflow board with exactly 5 connected agent cards: Research Agent, Strategy Agent, Content Agent, Design Agent, and Data Agent, linked by curved connector lines with small status chips such as Done and In progress. Below, include exactly 4 metric tiles: “2.4M+ Tasks automated”, “180K+ Agents this month”, “98.6% On-time”, and “4.9★ User rating”. Under the metrics, include a row labeled “Connects with the tools you use” with exactly 7 integration icons/buttons: Slack, Notion, GitHub, Figma, Google Drive, HubSpot, and “+ More”. Add a testimonial block with a circular female headshot and the quote “AgentBoard gives us complete visibility and keeps our team aligned.” credited to Sarah Chen, Head of Product, Northline. At the bottom, include exactly 4 feature blurbs with tiny line icons: Visual workspace, Multi-agent collaboration, Real-time progress, and Secure & governed. Right screen, product dashboard: Create a dense but elegant web app interface. Top app bar shows “AgentBoard” on the left, main tabs Workspace, Agents, Integrations, Data, Reports, plus an Invite button, a row of 5 small user avatars, a “+3” badge, and a dropdown chevron. Left sidebar for workspace “Acme Inc.” with exactly 11 navigation items: Home, Inbox with an 8 badge, Boards, Agents, Workflows, Data, Reports, Integrations, Settings, Help, and Collapse. Main page title reads {argument name="dashboard title" default="Q2 Go-to-Market Launch"} with a green “Live” pill and subtitle “Coordinating agents across research, strategy, content, design, and ops.” Include Share and dark green Add agent buttons. Dashboard content: Below the title, show exactly 4 tabs: Board, Progress, Outputs, Activity, with Board active. The main board canvas contains exactly 6 connected workflow cards arranged left-to-right with curved connector lines: Research Agent “Market & audience research” Done; Data Agent “Performance analysis” Done; Strategy Agent “Go-to-market plan” In progress; Content Agent “Messaging & content framework” In progress; Design Agent “Creative concepts & brand” In progress; Ops Agent “Launch readiness & checklist” In progress; Analytics Agent “Performance forecast” Queued. Include small board controls at top right: search icon, layout icon, fit icon, zoom “100%”, and dropdown. Under the board, add a KPI strip with exactly 5 items: Live progress 72% with green progress bar, 9 Active agents, 24 Tasks running, 156 Tasks completed, and 92% On-time, plus a “View all runs” button. Add a Recent outputs section with exactly 4 document cards: GTM Strategy Brief, Messaging Framework, Creative Concepts, and Performance Forecast, each with a small preview thumbnail and update time. Add a Recent runs table with exactly 5 rows: Q2 Go-to-Market Launch, Customer Onboarding Revamp, Pricing Strategy Analysis, Brand Refresh Campaign, and Enterprise Sales Playbook; include tiny agent avatar clusters, colored status pills, started times, and durations. At the bottom, include a Composer input bar with placeholder “What would you like the agents to work on?”, buttons for Attach and Add context, an “All agents” dropdown, and a green send button. Visual style: Premium minimal product mockup, realistic UI proportions, crisp vector-like rendering, tiny legible interface text where possible, subtle dotted background texture, pale beige cards, green status indicators, fine connector lines, modern editorial SaaS aesthetic suitable for a product-design exploration tweet. Constraints: Use exactly 2 main screens, exactly 5 agent cards on the landing hero, exactly 4 metric tiles, exactly 7 integration icons, exactly 4 bottom feature blurbs, exactly 11 sidebar items, exactly 4 dashboard tabs, exactly 6 workflow agent cards on the dashboard board plus the queued Analytics card as the seventh endpoint, exactly 5 KPI items, exactly 4 output cards, and exactly 5 table rows. Do not add extra panels, watermarks, browser chrome, or decorative text beyond the described UI.

Goal: Create a dark futuristic dashboard infographic for local AI model recommendations titled {argument name="headline text" default="LLMFIT RECOMMENDATIONS"}, with a large central panel reading {argument name="main title" default="LEGION MODEL LOADOUT"}. The design should look like a cyberpunk hardware-analysis UI generated on demand for a local machine, not a marketing poster. Canvas: Wide 21:9 landscape image, approximately 1200x560, black and deep teal background with subtle glow, thin cyan grid lines, faint circuit traces, and a bordered application-window frame. Add a small close-box icon in the top right of the window. Use sharp sci-fi typography, condensed uppercase headings, neon lime accents, cyan outlines, and small amber annotation text. Top header: At upper left, small label "LEGION / MODEL INTELLIGENCE" above the headline. Under the headline, show hardware summary text: {argument name="hardware summary" default="NVIDIA GeForce RTX 5090 · 31.84 GB VRAM · 125.18 GB RAM"}. Main layout: Split the dashboard into two main columns. The left column takes about 70% width and contains the primary loadout card. The right column takes about 30% width and contains a compact verified-data list. Left primary card: Create a large neon-framed panel with the big title "LEGION MODEL LOADOUT" in lime green and white. Beneath it, show exactly 4 hardware capability badges in a single row: 1) NVIDIA GeForce RTX 5090, 31.8 GB VRAM with a GPU fan icon; 2) Intel(R) Core(TM) Ultra 9 285K with a CPU chip icon; 3) 125.2 GB system RAM with a memory module icon; 4) CUDA with a circular CUDA icon. Use lime for the GPU badge and cyan for the others. Loadout table: Below the badges, show exactly 6 ranked recommendation rows with large lime row numbers in rounded boxes and thin cyan separators. Each row should include model name, quantization, runtime, memory, and estimated speed. The 6 rows are: 1) "shawnw3j/Huihui-Qwen3.6-27B-abliterated-AWQ-MTP", quantization "AWQ-4bit", runtime "vLLM", memory "14.7 GB", speed "80.9 estimated tok/s"; 2) "Vortex5/G4-Starry-Ocean-12B", quantization "Q8_0", runtime "llama.cpp", memory "16 GB", speed "82.8 estimated tok/s"; 3) "shawnw3j/Qwen3.6-27B-AWQ-MTP", quantization "AWQ-4bit", runtime "vLLM", memory "14.7 GB", speed "80.9 estimated tok/s"; 4) "Minachist/Qwen3.6-27B-INT8-Autoround-V2", quantization "AutoRound-4bit", runtime "vLLM", memory "16.6 GB", speed "80.9 estimated tok/s"; 5) "exnivo/Qwen3.8-20B-Minitron", quantization "Q8_0", runtime "llama.cpp", memory "22.6 GB", speed "49.9 estimated tok/s"; 6) "Lorbus/Qwen3.6-27B-int4-AutoRound", quantization "AutoRound-4bit", runtime "vLLM", memory "16.6 GB", speed "80.9 estimated tok/s". Add tiny icons for chip, terminal/runtime, memory, and speedometer in the metric columns. Footer strip in the main card: Centered text in cyan: "ESTIMATED BY LLMFIT · VERIFY WITH A LOCAL BENCHMARK." Add angular brackets and thin decorative circuit segments around it. Right sidebar: Header "VERIFIED LLMFIT DATA" on the left and small amber text "ESTIMATES, NOT BENCHMARKS" on the right. Show exactly 6 compact verified-data rows matching the 6 recommendations, numbered 01 through 06 in lime. Each row should show a shortened model name, a small second line with quant/runtime/memory, and a large right-aligned score: 80.9, 82.8, 80.9, 80.9, 49.9, 80.9. At the bottom, add a small amber note: "llmfit recommendations are estimates from detected hardware, not measured benchmarks." Bottom window bar: Add tiny timestamp text at bottom left, "GENERATED 8/17/2026, 7:35:32 PM". Add a small rectangular neon green button at bottom right labeled {argument name="button label" default="Refresh scan"} with a refresh icon. Visual constraints: Keep all text in English, crisp and legible, with no extra rows beyond the specified 6 recommendations and no extra hardware badges beyond the specified 4. Use a dark transparent-glass UI style, subtle bloom, no people, no logos other than the textual hardware/model labels, and no watermark.

Create a charming minimalist 3D miniature {argument name="subject" default="coffee shop"} scene inspired by a cozy handmade paper-and-clay aesthetic. Place a tiny, beautifully designed coffee store in the lower-center of a large textured off-white paper background, leaving plenty of clean empty space around it. The coffee shop should look like a handcrafted miniature café: a small cream-colored storefront with a warm wooden counter, tiny espresso machine, coffee cups, pastries, coffee beans, little menu board, hanging sign, potted plants, stools, and subtle café decorations. Add a few tiny customers enjoying coffee and a barista behind the counter, keeping everything cute, delicate, and uncluttered. Use soft ivory, beige, warm brown, muted sage green, and subtle terracotta accents, with realistic soft shadows and gentle natural lighting. Add tiny hand-drawn black doodles around the café—small hearts, steam lines, stars, coffee beans, arrows, and simple decorative marks—to create a playful contemporary scrapbook feeling. The overall composition should feel premium, cozy, whimsical, handcrafted, and Instagram/Pinterest aesthetic, with a tactile textured-paper background, miniature diorama appearance, soft 3D details, lots of negative space, and a peaceful cozy coffee-shop mood. Vertical 4:5 composition, highly detailed, clean, elegant, photorealistic miniature craft style.

Using the provided reference image as the layout and poster-style guide, create a new vertical 3:4 high-end travel design poster with the same two equal horizontal sections, but replace the Venetian canal subject with {argument name="landmark" default="a Gothic twin-spired cathedral in Vienna at blue-hour night"}. Top section: show a cinematic realistic travel photograph of the landmark front-on at dusk/night, with warm architectural lighting, dark tree silhouettes on both sides, deep blue sky, and a single glowing infinity-shaped light trail wrapping around the two spire tops. Bottom section: transform the same landmark into a clean 3D isometric miniature diorama on a small square base, including exactly 2 tall illuminated spires, exactly 1 central cathedral building, exactly 6 surrounding trees, paved plaza tiles, warm doorway/window lights, and the same glowing infinity light trail around the spires. Keep the minimal cream editorial background and soft shadows like the reference poster. Typography and graphic details: place a left-aligned title block in the lower half with the headline {argument name="headline text" default="INFINITE FAITH"}, a thin horizontal divider line beneath it, and the small caption {argument name="caption text" default="LIGHT CONNECTS\nWHAT TIME CANNOT."}. Add a small bottom-left label {argument name="series label" default="No. 011\nEvening Series"}. Add a small compass icon on the right side of the lower half, and place bottom-right coordinates and city text {argument name="location text" default="48.2196° N, 16.3656° E\nVIENNA"}. Use elegant serif typography, restrained spacing, premium museum-poster aesthetics, realistic-to-miniature transformation, no collage, no extra panels, no watermark.

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体结构、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物与展览摄影质感。为适配画幅，可自然扩展天空、地面或环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的**主体、轮廓、姿态与叙事关系**，以 **isometric / 轴测式3D空间逻辑**重构为精致的厚涂微景观。主体不是平面插画，而是具有明确体积、结构、前后关系和稳定落点的立体微缩实体；保留原物最关键的身份特征，可适度整理视角与比例，使其在统一轴测空间中更加完整、清晰、有雕塑感。 主体坐落在一块由厚涂颜料形成的**主题色域**之上。色块不是普通矩形背景，而应根据原图内容转化为水面、地面、道路、草地、光带、岸线、影子或其他与主题相关的空间切片，并沿 isometric 透视方向自然延伸。主体必须与色块发生真实空间关系，可出现落地、嵌入、穿越、延伸、倒影、波纹、投影或局部越界，使二维厚涂笔触与三维主体巧妙连接。 构图依据主体的体量、朝向和运动方向自适应安排，以**斜向轴测、稳定重心、前后纵深和大面积留白**建立专业空间秩序。主体通常位于色块的关键节点而非机械居中，色块承担视线引导和透视延伸；必要时可加入一组低权重的云、太阳、植物、波纹或抽象自然意象，与主体形成前后层次，但不建立第二视觉中心。 绘画语言采用**立体微缩模型 × 厚涂油画 × 真实纸面**的融合方式。主体细节精致、体积清晰，周围环境则保留明显的刮刀痕迹、厚颜料堆积、起伏边缘和手工笔触；云、水、地面和光线可以具有近似浮雕般的油彩厚度，使画面产生“真实模型立在尚未干透的油画颜料上”的触觉错觉。 配色从上方照片中提取**最明亮、最鲜活、最能代表主体精气神的颜色**重新调制，提高明度、纯净度和生命力，以大量清洁暖白作为呼吸空间，搭配清透主色和少量阳光般的暖色点睛。整体明亮、治愈、鲜活而高级，避免灰脏、低沉、莫兰迪化、荧光感和廉价糖果色。 文字少量介入，从照片的主体、地点、情绪或象征意义中提炼简短标题，并搭配极少量副文、编号或微型注释。排版保持细致、克制，可顺应轴测方向、厚涂色块边缘或留白区域排列，与空间透视形成巧妙呼应，而不是独立贴在画面上的标题。 整体呈现 **isometric 立体主体 × 厚涂色域 × 明亮治愈配色 × 真实纸张 × 大面积留白** 的视觉关系。无论主体是建筑、人物、动物、植物、器物、交通工具或自然景观，都应让三维主体真实“站立、生长或存在”于厚涂色块构成的空间中，避免平面贴图、普通插画、塑料CG、玩具模型感和模板化微景观。

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体结构、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物和展览摄影质感。为适配画幅，可自然扩展天空、地面或环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的**主体、轮廓、姿态与叙事关系**，以 **isometric 等距空间逻辑重新构建**。不是把原物简单变成3D模型，而是将主体拆解为清晰的体块、层级、切面与空间关系，在统一等距轴线中重新组合，使其兼具建筑模型般的结构秩序与编辑插画般的视觉概括。可适度调整观察角度、比例和局部结构，以更好地展示主体最有代表性的形态，但必须保持一眼可识别的身份特征。 同时从照片的核心内容、动作、结构或象征关系中提炼一个**主题意象**，将其几何化、符号化并融入isometric构图。主题意象可以成为底座、切面、空间缺口、路径、包围结构或负形，让主体与其发生穿越、嵌合、悬浮、切割、承托或错层关系，使主题不是附加装饰，而是决定主体如何存在于空间中的构图机制。 构图根据主体的视觉重心、轮廓走势 and 空间特性自适应设计，通过等距轴线、体块比例、层级错落、尺度反差、局部裁切和大面积留白建立专业秩序。主体不必机械居中，可偏置、悬浮或延伸，让isometric结构与主题意象共同形成唯一视觉中心。 主体采用**高明度、清透、柔和的日系配色与细腻哑光材质**。颜色从上方照片中提取最有生命力、最能代表主体精气神的色彩重新调制，以柔白、奶油白或极浅暖色作为基础，将核心色转化为干净、明亮、轻柔的色面，通过同色深浅和少量点色区分不同体块。光影柔和而明确，用轻微明暗帮助读取结构，避免厚重3D阴影、塑料材质和灰脏色调。 背景保持大量留白，并加入**达·芬奇手稿式的创作研究痕迹**：与主体相关的轮廓草图、结构拆解、局部放大、比例线、测量线、箭头、几何推演、自然观察线稿和微型注释，以极淡的铅笔、赭色墨线或褪色手稿质感若隐若现地分布在主体周围。手稿应像设计过程留下的思考轨迹，与精确的isometric主体形成“理性成品与感性研究过程”的对照，不形成第二视觉中心。 文字同样围绕主题和空间结构组织。从照片的主体身份、动作、情绪或象征意义中提炼一个简短英文标题，并搭配极少量地点、状态词或微型注释。文字可以沿isometric轴线、主题意象边界、结构切面或手稿辅助线排列，横排、竖排、错位、穿插或隐藏于负形中，使文字像设计图纸和高级艺术出版物中的信息层，而不是后期贴上的标题。 整体呈现**主题隐喻 × Isometric空间秩序 × 达·芬奇式研究手稿 × 日系清透色彩 × 东方留白 × 高级编辑设计**的视觉气质。无论主体是人物、动物、植物、建筑、器物、食物、交通工具或自然景观，都应以其自身结构找到最合适的等距重构方式，避免普通3D模型、游戏场景感、轴测工程图感、卡通低多边形、机械居中、电商展示感和模板感。

Using REFERENCE_0 as the exact floor plan, convert the flat black-and-white 2D apartment layout into a realistic furnished 3D dollhouse/top-down cutaway rendering. Preserve the same room arrangement, wall positions, openings, doors, closets, and major furniture placement, but extrude the walls into thick dark gray 3D walls and replace the schematic symbols with believable modern furniture and decor. Style: photorealistic architectural visualization, warm neutral interior design, light wood flooring throughout, soft beige and white furnishings, realistic shadows, top-down isometric perspective on a clean white background. Layout to preserve: exactly 7 labeled zones from the plan — 2 bedrooms, 1 living area, 1 kitchen, 1 bathroom, 1 entry area, and 2 closet/storage zones including the laundry closet. Keep the kitchen island with 3 stools, living sofa and lounge chairs, dining table, two beds, bathroom fixtures, closet shelving, washer/dryer area, and entry corridor in their corresponding locations. Additions and conversion details: turn all doors into open wooden hinged doors, add realistic windows along the bottom exterior wall, add rugs under beds and seating areas, add closet clothing/shelves, add countertops, sink, stove, refrigerator, bathroom vanity, bathtub/shower curtain, toilet, small plants, lamps, pillows, and subtle decor. Keep only the visible laundry text {argument name="laundry label" default="WASH DRY"} on the washer/dryer surface; remove other floor-plan room labels and blueprint linework. Constraints: no people, no exterior landscaping, no extra rooms, no major layout changes, no exaggerated colors, maintain the same apartment footprint and orientation as the reference.

3D render of {argument name="subject" default="[SUBJECT]"}, stylized hand-painted 3D game asset, chunky simplified geometry, broad readable shapes, softly beveled edges, matte painted wood and metal, subtle hand-painted surface variation, restrained material detail, deep plum and burgundy wood, dark teal and navy hardware, selective crimson and muted warm accents, soft diffuse lighting, gentle ambient occlusion, simple soft directional shadow, flat solid black background, no vignette, no dramatic lighting, no volumetric effects, elevated isometric three-quarter view, clean centered composition, compact game-ready silhouette, understated handcrafted atmosphere.