Software Architecture Visualization Diagram

Japanese Architectural Concrete Studio Fashion Campaign

Stunning young Japanese woman in a high-end fashion studio photoshoot, standing gracefully in a cont…

Cloud AI Agent Architecture Diagram

enterprise cloud AI architecture infographic · clean corporate vector diagram, white background, blue and teal palette, rounded rectangles, thin blue outlines, subtle shadows, Chinese-first bilingual labels with smaller English subtitles, symmetrical layout, presentation-slide quality · 4:3 · 1024x768 · {argument name="headline text" default="云端 AI Agent 架构图"} · 面向云端任务执行、代码协作与大规模调度的 Cloud AI Agent Architecture · top center · stacked architecture layers · 7 · true · 1 · 接入与体验层 · access and experience layer · 5 · Web Console, IDE / CLI, API / SDK, 消息通知 Slack / Email, 任务看板 组织与项目空间 · 2 · 云端控制平面 · cloud control plane · 6 · API Gateway, Auth / Tenant, Session Manager, Project / Workspace Manager, Task Queue, Rate Limit / Billing · 3 · Agent 编排层 · agent orchestration layer · 8 · Planner / 任务规划器, Reasoner / 推理引擎, Context Manager / 上下文管理, Memory / 记忆系统, Prompt Builder, Workflow Orchestrator / 工作流编排, Policy Engine / 策略引擎, Multi-Agent Coordinator / 多 Agent 协同 · 4 · 执行运行时层 · execution runtime layer · 8 · Sandbox Pool / 容器沙箱, Browser / HTTP 工具, Code Runner / Terminal, Git Workspace, Tool Adapters / MCP, Scheduler / Worker, Test Runner, Artifact Executor / Patch & Diff · 5 · 模型与智能服务层 · model and intelligence services layer · 6 · Model Router, Frontier LLM API, Embedding / Reranker, OCR / STT / TTS（可选）, Evaluator / Reflection, 第三方 Agent / SaaS · 6 · 数据与状态层 · data and state layer · 8 · Relational DB, Vector DB, Redis Cache, Session State, Artifact Store, 对象存储 Object Storage, 配置中心 Config, 日志与审计 Logs · 7 · 云基础设施层 · cloud infrastructure layer · 8 · Kubernetes / 容器编排, Service Mesh, Event Bus, Secrets / KMS, VPC / Network, Autoscaling, CI/CD, 多区域容灾 DR · 可观测性 / SRE · left · 6 · 监控 Monitoring, Tracing, Metrics, 日志聚合 Logs, 成本与配额 Cost / Quota, 告警 Alerting · 安全治理 · right · 6 · SSO / RBAC, 密钥与 Secrets, 策略护栏 Guardrails, 人工审批 Human Approval, 审计合规 Audit, 数据隔离 Isolation · bidirectional blue arrows linking both sidebars to every central layer, plus vertical arrows between each architecture layer · simple blue line icons in every box, one icon per module · rounded white cards with pale blue or pale green tinted section backgrounds · light blue · light lavender · light cyan · light green · deep royal blue headers with white text · bold dark navy Chinese headline, smaller gray-blue subtitle, medium-weight Chinese section labels, compact bilingual item labels · bottom center · {argument name="footer text" default="特性：云原生 • 多租户 • 弹性扩缩容 • 安全合规 • 人机协同 • 任务可追踪 • 支持多模型与多 Agent 协同"} · crisp infographic, balanced spacing, high legibility, polished enterprise architecture slide suitable for keynote, documentation, and product marketing

Neural Network Architecture Diagram

Generate an entire large resolution diagram that dictates the entirety of the {argument name="model name" default="NanoGPT"} architecture.

Infrastructural Typography Architecture

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

Gothic AI Stack Diagram

Goal: Create a dark gothic hand-painted infographic poster titled {argument name="headline text" default="THE AI STACK"}, showing an interconnected personal AI-tool stack as a mysterious occult network. Canvas: Square 1:1 composition, black and charcoal textured canvas with visible rough brush strokes, scratched chalk marks, muted cream ink, and subtle sepia highlights. The mood is eerie, nocturnal, vintage, and slightly haunted. Layout: Place a large central circular node labeled {argument name="main tool" default="CLAUDE"} with a simple eight-point starburst symbol inside it. Four rounded rectangular tool cards connect to the central node with pale hand-drawn cables and small circular connector dots. Use exactly 4 outer cards: top-left card labeled {argument name="tool 1" default="CODEX"} with a browser-window code icon, top-right card labeled {argument name="tool 2" default="GPT IMAGE 2"} with a framed landscape/image icon, bottom-left card labeled {argument name="tool 3" default="ANTIGRAVITY"} with a starry mountain or sparkling night icon, and bottom-right card labeled {argument name="tool 4" default="HERMES"} with a crossed-arrows or janitor-like routing symbol. Keep all text in uppercase, widely spaced, distressed serif/typewriter lettering. Scene details: Add a glowing full moon centered above the main node, a small spiderweb and tiny spider in the upper-left corner, a dark gothic castle silhouette in the right background, fog and smoky clouds along the bottom, a wilted flower with a bent stem leaning across the left side of the central node, one fallen brown leaf near the base of the flower, and an antique skeleton key lying at the bottom right. Include a tiny creator handle centered at the bottom: @AunySillyMe. Visual style: Painterly gothic chalkboard illustration, rough impasto texture, off-white linework on black, muted gold-brown accents on the dead flower and leaf, softly glowing moon, handmade imperfect borders, no clean vector polish. Constraints: Use exactly 1 central circle, exactly 4 connected outer cards, exactly 4 outer tool labels, exactly 1 moon, exactly 1 spiderweb, exactly 1 spider, exactly 1 wilted flower, exactly 1 fallen leaf, exactly 1 castle silhouette, and exactly 1 key. Do not add extra cards, extra tools, bright colors, modern UI gloss, or photorealism.

Handcrafted String Visualization 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{argument name="比例" default="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 and 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。 下半部分提取照片中最具识别性的**主体、轮廓、结构、姿态与叙事关系**，将其转译成一张真实可触摸的 **{argument name="风格" default="Physical String-based Systems Map / Tangible Node-link Visualization"}**。不要直接描绘原物，而是把主体拆解为少量具有意义的节点与关系：关键轮廓、结构转折、动作方向、空间位置或环境线索成为图钉式 Nodes，彼此之间使用真实线绳作为 Edges / Links，使原照片的视觉关系重新以实体网络显形，并仍能隐约辨认出原主体的身份与结构。 构图以一个明确的**核心节点或核心关系**作为视觉枢纽，其余节点围绕主体结构自然展开。线绳不是随机缠绕，而应根据原图的方向、比例、远近、连接与叙事逻辑建立关系；部分节点形成放射、聚合、三角、多边形与跨区域连接，使大量简单关系自然产生 **emergent geometry**。整体既复杂又有秩序，中心关系较密，外围逐渐疏松，保留充足负空间，避免把整个版面铺满。 材质必须具有真实实体装置感：使用细小图钉、针脚、棉线或细绳、纸质标签、手写痕迹 and 真实纸板表面，保留轻微线绳松紧差异、节点高度、交叉遮挡、针脚阴影与手工误差。整体像一件经过艺术指导的研究墙、系统设计实验或信息艺术装置，而不是电脑绘制的网络图，也不要出现赛博UI、数字发光线或廉价侦探板效果。 线绳以**鲜明但克制的{argument name="线条色" default="朱红、珊瑚红或暖红色"}**作为主要关系色，在大量自然白、暖白、浅灰或与上方照片综合色温协调的极浅背景中形成视觉张力；图钉、纸签与少量标记可从上方照片提取局部特征色进行低面积呼应。整体颜色干净、现代、有生命力，避免暗褐、脏旧、血红恐怖感 and 过度复古做旧。 文字作为系统中的**Hand-lettered Annotation** 自由介入，不预设固定标题、地点、年份或菜单式信息。根据照片中的主体、动作、位置、情绪、关系或隐喻，自由生成少量关键词、短句、箭头、圈注或微型说明，并直接写在节点附近、线绳交汇处或留白区域。字体使用**细小、松弛、略带研究笔记感与书写偏差的手写注释字体**，让文字像观察过程中自然留下的思考痕迹，同时保持高级编辑设计的克制与可读性。 整体呈现**实体节点、红色线绳、关系映射、涌现几何、手写注释与大量留白**共同构成的高级实验视觉。无论主体是人物、动物、植物、建筑、器物、交通工具、自然景观或复杂场景，都应把“它是什么”进一步转译为“它的各部分如何发生关系”，形成具有研究感、艺术感、系统性与手工温度的实体信息可视化。避免随机红线、无意义节点、满版混乱、恐怖犯罪板、数字网络UI、卡通图钉、模板化思维导图 and 普通流程图。 😌🥲😘

Act as a 3D Product Visualization Artist

[BRAND NAME]. Act as a 3D Product Visualization Artist. PHASE 1: LOGO TO 3D OBJECT Take the [BRAND NAME] logo and transform it into a thick 3D sculptural form. Simplify to core shape, add rounded edges (8-12mm fillet), make it one solid piece with 40-60mm depth. Keep it recognizable. PHASE 2: PINK METALLIC MATERIAL - Color: Pink metallic (#C85A8E to #8B4A6F range) - Finish: Glossy brushed metal with fine grain - Highlights: Light pink (#E89BB8) - Shadows: Deep plum (#6B3854) - Roughness: 0.2 (shiny but not mirror) - NO copper, NO gold, NO silver PHASE 3: LIGHTING Soft studio lighting from top-left creating smooth gradient across the object. Light pink on highlights, deep plum in shadows. No hard shadows. PHASE 4: BACKGROUND & FLOATING - Pure white background (#FFFFFF) - Object levitating in white void - Soft blurred shadow underneath (90% transparent) - NO pedestals, NO stands, NO supports PHASE 5: CAMERA Slight 3/4 angle, looking down 10°, object centered, filling 60% of frame. TECH SPECS: - High-quality 3D render (Octane/Cycles) - 4K resolution - Full object in focus - Subtle bloom on highlights CRITICAL: - Must be PINK metallic only - Must float in pure white space - Must have thick 3D volume with smooth surfaces - Must look like luxury product photography

Act as a Senior 3D Product Visualization Artist and Cinematic Art

[BRAND NAME]. Act as a Senior 3D Product Visualization Artist and Cinematic Art Director specializin…

Japanese Minimalist Concrete Studio Fashion Editorial

Stunning young Japanese woman in a high-end fashion studio photoshoot, standing gracefully in a cont…

YOLOv13 Architecture Diagram

Goal: Create a clean technical architecture diagram explaining {argument name="model name" default="YOLOv13"} as a one-page educational slide, showing how an input image flows through Backbone, HyperACE, Neck, FullPAD, and Head detection outputs. Canvas: Wide 16:9 landscape infographic on a white background, crisp vector style, thin colored outlines, rounded rectangles, arrowed connectors, and readable sans-serif text. Use a left-to-right pipeline with supplementary modules below the main path. Layout: Start at far left with a small stacked thumbnail illustration labeled “Input Image (3, H, W)”, then an arrow into a large blue Backbone panel. Place the green Neck panel in the upper center, the purple Head panel on the right, HyperACE in the lower left-center, FullPAD in the lower center-right, and a boxed explanatory caption along the bottom. Main pipeline sections and exact element counts: - 1 Input Image stack at far left, shown as layered landscape photos. - 1 Backbone panel titled “Backbone” with subtitle “(built from DS-C3k2 blocks)”. Inside it, show exactly 5 vertically stacked DS-C3k2 block boxes labeled B1, B2, B3, B4, B5. Put “/2” downsampling markers between each adjacent block, for exactly 4 downsampling labels. Add side output arrows: B1 and B2 go right and are labeled “B1 (unused)” and “B2 (unused)”; B3, B4, and B5 go right in blue and are labeled “B3 (C3, H/8, W/8)”, “B4 (C4, H/16, W/16)”, and “B5 (C5, H/32, W/32)”. - 1 HyperACE module below the Backbone, orange outline, titled “HyperACE” with subtitle “(Hypergraph-based Adaptive Correlation Enhancement) Eq.8-11”. Inside it, include one dashed rounded note box saying “Models cross-scale and cross-position high-order and low-order correlations”. Blue lines from B3/B4/B5 feed into HyperACE. HyperACE outputs an orange arrow to a small orange 3D cube labeled “Y” and “Correlation-enhanced feature”. - 1 Neck panel in the upper center, green outline, titled “Neck” with subtitle “(built from DS-C3k2 blocks)”. Inside it show exactly 6 DS-C3k2 block boxes arranged in a 2-column by 3-row grid. Use black arrows between blocks, with exactly 2 yellow upsample boxes labeled “↑ 2×” and exactly 2 purple downsample boxes labeled “↓ 2×”. Include 3 blue circular input junctions on the left edge of the Neck and 3 green/purple circular tunnel markers below or beside the grid. - 1 FullPAD legend module below the Neck, red outline, titled “FullPAD” with subtitle “(Full-Pipeline Aggregation-and-Distribution) Eq.12-13”. Show exactly 3 legend rows: “Backbone–Neck tunnel (Backbone-to-Neck connection)” using blue dotted arrows and blue hollow circles; “In-Neck tunnel (the internal layers of the Neck)” using green dotted arrows and green hollow circles; “Neck–Head tunnel (Neck-to-Head connection)” using purple dotted arrows and purple hollow circles. Connect the cube feature into FullPAD with an orange arrow, and draw dotted blue/green/purple tunnel routes upward and rightward to the Neck and Head. - 1 Head panel on the right, purple outline, titled “Head” with subtitle “(Detect x3)”. Inside it show exactly 3 vertically stacked Detect boxes: “Detect (stride 8)”, “Detect (stride 16)”, and “Detect (stride 32)”. Each receives one arrow from the Neck and outputs to the right as H3, H4, H5 with labels “H3 (scale 1/8)”, “H4 (scale 1/16)”, and “H5 (scale 1/32)”. Color coding: Backbone lines and panel in blue, Neck in green, Head in purple, HyperACE in orange, FullPAD outline in red. Main arrows are solid; FullPAD tunnels are dotted/dashed with hollow circular nodes. Use subtle pastel fills for module boxes. Bottom caption: Add one wide rounded rectangle spanning the lower width. Text: “Classic YOLO is a one-directional Backbone → Neck → Head pipeline.” Then on the next line: “{argument name="model name" default="YOLOv13"} adds HyperACE and FullPAD on top of it to enhance feature representation and information flow.” Color the words Backbone blue, Neck green, Head purple, HyperACE orange, and FullPAD red. Constraints: Keep all labels legible, align sections neatly, preserve the exact counts of blocks and detect heads, avoid extra modules, avoid photorealism except for the small input image thumbnail, and do not add a watermark.

Isometric Diorama Topology Visualization

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.

Chat-based persona visualization

{argument name="分析元" default="私のチャット履歴"}から、私がどういう人物なのか想像してください、そしてそれをimage2.5で画像にして、あなたが私をどう思ってるのか知りたい

Futuristic Chinese Architecture Fusion

中式留白的未来主义杂交的中式美建筑::东方山水的可望可游可居::借景、框景、障景、留白::建筑现象学与场所精神::安藤忠雄的静默几何::路易斯·康的纪念碑性::卡洛·斯卡帕的细部边界意识::阿尔多·罗西的原型与记忆::批判地域主义::极简主义体块与大面积空场::图底关系::崇高美学::遮蔽与显露::宏伟建筑尺度::总有一处清晰受光::深阴影、雾气、空气透视::低饱和综合色彩::至少一个高辨识彩色元素作为视觉锚点::克制、寂静、神圣、未被解释的超现实空间::电影级获奖镜头构图::超广角镜头 主题：{argument name="主题" default="嫦娥奔月"} 比例16:9

Vacant Property Real Estate Visualization

店舗種類：{argument name="店舗種類" default="生活雑貨"} 、状態：{argument name="状態" default="グランドオープン"}、駐車場：{argument name="駐車場" default="配送トラック"}

You are a world-class director of industrial visualization

You are a world-class director of industrial visualization and a futuristic interface designer specializing in advanced visual engineering diagnostic tools. Your task is to transform the downloaded product into a futuristic visualization of the technical scanning interface, similar to the product analyzed in a high-tech laboratory diagnostic system. input: uploaded product image style: • black background with a clear white grid of the drawing • the product is made in the form of a luminous translucent X-ray frame model • clear geometry of the technical grid • Ultra-sharp white lines and edges • Minimalistic HUD interface design in sci-fi style INTERFACE ELEMENTS: • thin white lettering-callouts with pointer lines describing the components of the product • Zoom analysis field, showing a product fragment in close-up • A colored layer of the heat map of the material (red/ orange/blue) is displayed inside the zoom field. • Scan indicators such as: "THE SCAN..." "MATERIAL ANALYSIS..." "98% DATA PROCESSING" • Small loading panels and user interface diagnostic modules • luminous markers in the form of angular frames around the image VISUAL LANGUAGE: • Advanced engineering drawing design • Futuristic laboratory scanning interface • Engineering visualization of the product at the Apple level • Ultra-pure composition • High-contrast black and white interface lighting: • subtle white glow around the frame • Volumetric light beam scanning • Technical sci-fi visualization composition: • in the center of the product • Grid-aligned interface layout • Scalable analysis panel in one corner • Minimalistic but highly technical exit: Futuristic product scanning interface , visualization of technical diagnostics , technical analysis screen , ultra clean, ultra clear, 8K

Historic Battle Visualization Scroll

生成一张【经典战役可视化长卷】，单张完整图片，不要拼图，不要多宫格，不要分栏，横版 3:1。 战役主题：【{argument name="战役主题" default="赤壁之战"}】 标题：【{argument name="标题" default="赤壁之战"}】 副标题：【{argument name="副标题" default="一句话概括关键转折"}】 核心内容：【战场地形 / 双方阵营 / 主攻路线

Desktop AI Agent Architecture Diagram

{"type":"bilingual enterprise architecture infographic","topic":"{argument name=\"headline text\" de…

Kafka Architecture Diagram

{argument name="技术主题" default="kafka"}架构图 明确显示原理 包含核心组件

Brutalist Monolithic Architecture Portraits

Desert Brutalism & Monolithic Earth Architecture, {argument name="architecture style" default="Rick Owens Architectural"} × {argument name="subject" default="Pedro Pascal"} "{argument name="title" default="MONOLITH OCHRE"}"

Character Relationship Diagram Poster Generator

请根据{argument name="主题" default="鬼灭之刃"}，生成一张高设计感的人物关系图海报。要求这张图不是普通插画，而是兼具信息可视化、叙事结构、海报设计感和作品风格还原度的人物关系图。 请自动完成以下内容： - 识别该主题对应的作品及其核心设定 - 提取最具代表性的 6–12 位关键人物，必要时不超过 15 位 - 识别并展示关键人物关系，包括血缘、爱情、友情、联盟、敌对、师徒、主从、操控、背叛、秘密关系等 - 自动按作品特点选择合适的构图方式，如主角中心型、双核心对峙型、阵营分区型、家族谱系型或时间演变型 - 自动提炼作品的风格DNA，包括色彩、世界观符号、材质纹理、情绪氛围、排版语言和代表性元素 - 将这些风格元素转化为人物关系图的整体视觉设计，而不是简单复制某张官方海报 - 用不同颜色、线型、箭头区分不同关系，保证线条清晰、层次分明、不杂乱 - 核心人物最突出，重要人物次之，次级人物弱化，形成明确视觉层级 - 每个人物名称清晰可读，必要时可加入身份或阵营标签 最终成品应满足： - 一眼看懂人物主次和关键关系 - 具有明显的原作品气质与设定感 - 兼具信息图的清晰度与海报的高级设计感 - 画面统一、精致、完整、适合社交媒体传播或海报展示 - 避免廉价流程图感、避免杂乱堆砌、避免信息过载

Geometric Line Art Architecture Poster

请根据最后输入的主题，创作一张**超高分辨率、可打印的 3:4 竖版海报**。整体采用上下两个区域的双联结构，**上下高度严格 1:1，各占画面 50%**。 **上半部分**根据{argument name="主题" default="城市"}生成一幅完整、统一、真实且富有生活感的场景画面。若主题是城市，请先理解其核心气质，从空间景观、街头生活、人文风情、商业氛围、饮食记忆、地方文化、历史层次与日常节奏中提炼视觉线索，并自然组织进同一幅真实而鲜活的城市切面中，而不是零散拼贴。若主题是具体街道、街区、地标、商圈、店铺、建筑或代表性地点，请以真实空间关系为核心，准确呈现街道结构、建筑界面、店铺招牌、交通设施、文字系统、人群状态与现场氛围，保留其最有辨识度的在地特征。若主题包含地址、坐标或参考图片，请优先依据真实信息理解场景，不要凭空杜撰，不要随意替换地点特征，也不要画成与主题无关的通用景观。整体避免廉价旅游宣传和明信片式表达，而应捕捉一个克制、精致、真实、具有日常温度的主题瞬间；人物、建筑、街道、标牌、橱窗、设施与活动自然共生，地标融入环境，不夸张、不喧宾夺主。 **下半部分**提取上半部分画面中**最具识别性的主体、轮廓、结构、姿态与叙事关系**，重构为一幅**极简线条图形化表达**。不要机械描摹细节，而是以纤细准确的单线、清晰几何透视、克制留白、有秩序的细节节奏和适度抽象的概括造型重新表达，保留一眼可识别的主题特征。若主题偏城市或地点，可提取其最关键的建筑天际线、街道界面、标牌节奏、交通设施、橱窗关系或人群状态；若主题不是城市，也应提取其最核心的身份特征、轮廓语言、结构关系与视觉记忆点，并转化为统一、简洁、现代、高级的线描海报语言。可加入少量几何辅助元素、水平线、纵向构成线或节奏性留白，使下半部分像是对上半部分现实场景的提炼与再设计。 **文字系统**需要自然融入整体版式，延续这种克制、高级、现代的海报逻辑。顶部设置醒目的主标题；副标题可使用主题原文、当地语言、国家或地区信息、地址、坐标、编号、年份或一句简短说明。若画面包含街头文字、招牌或地点信息，必须清晰、自然、真实、专业，避免乱码、错误文字与随意拼写。文字排版应简洁有秩序，与画面共同构成收藏级旅行海报与城市品牌视觉般的完成度，而不是后期随意贴上的说明标签。 色彩不要机械套用固定模板，而应先理解主题本身的气候、光线、时间感、建筑材料、历史气息、商业温度、饮食印象、自然环境与情绪质地，再提炼出**专属于该主题**的主色与底色关系。整体可采用单色印刷美学或极少量克制配色，通过线条疏密、明度层次、局部压重、留白比例与细节节奏形成丰富变化，避免单调和平铺。最终成品应呈现**线条清晰、细节丰富、风格统一、安静现代、灵动克制、审美高级**的海报效果。

Highly detailed isometric 3D rendering of in architectural visualization

Create a highly detailed isometric 3D rendering of [LANDMARK] in architectural visualization style. The building is shown at a 45-degree angle from above, displaying three visible sides with intricate architectural detail. Photorealistic textures showing materials like stone, glass, metal, or brick. Include the base/ground level with tiny people, cars, and landscaping for scale. Clean white or light grey background. Professional architectural rendering with soft ambient shadows beneath the structure. Every window, column, ornamental detail, and structural element clearly visible. 1080x1080 dimension, centered composition. Style similar to video game building assets or architectural presentation models - clean, detailed, slightly stylized but realistic.

Split architectural visualization where the top is a detailed

{ "objective": "Create a split architectural visualization where the top is a detailed dark-themed…

Nested Picture-in-Picture Software UI

生成一张具有视觉纵深感的‘画中画’图像。最外层是一个真实的 {argument name="编程界面" default="VSCode 编程界面"}，中间嵌套一个{argument name="应用名称" default="千问App"}的聊天界面，聊天界面里我正在发送一条消息，内容是‘{argument name="生成请求" default="帮我生成一张手冲咖啡海报"}’。千问回复了一张精美的咖啡海报，这张海报也清晰地显示在聊天界面中。要求每一层UI都保持真实的风格与细节，界面中的时间数字、按钮小字等微观细节清晰可辨。

Ultra-Realistic Cinematic Spotlight Portrait

Use the reference image as the identity of the person, preserving the exact facial features, face shape, hairstyle, beard, skin tone, proportions, and overall identity while recreating the same artistic composition, illustration style, and visual energy. Ultra-realistic cinematic portrait of a {argument name="subject" default="stylish man"} in a {argument name="outfit" default="black suit"}, captured from behind with his head turned over his shoulder, giving a sharp, intense look toward the camera. {argument name="hair style" default="Short textured hair with subtle highlights"}, well-groomed beard. Dramatic spotlight from above creating a warm golden halo effect on his hair and face, fading into a dark background. Strong chiaroscuro lighting with deep shadows and soft highlights. Aspect ratio 4:3. Add the watermark

Kawaii Cactus Sticker

Create a cute printable sticker illustration on a transparent background: a kawaii green cactus in a terracotta flower pot, centered and filling most of a square canvas. The cactus has one large oval ribbed central body and exactly 2 curved side arms, one on the left and one on the right, both raised upward. Give it a happy face with exactly 2 glossy black oval eyes, 2 pink circular blush cheeks, and 1 open smiling mouth with a dark interior and pink tongue. Add a red-pink flower on top-left of the cactus with exactly 6 rounded petals and a cluster of small yellow dots in the center. Cover the cactus with many small star-shaped cream spines with orange bases, distributed across the main body and both arms. Place the cactus in an orange terracotta pot with a thick rim, darker orange shading, small speckles, and glossy highlights; show brown soil and several rounded pebbles at the top. Use a polished digital cartoon style with thick dark green outlines, soft gradients, shiny highlights, saturated colors, and a clean die-cut sticker look with a thick white border around the entire cactus and pot. Background should be transparent, optionally previewed by a light gray checkerboard only to indicate transparency. No text, no watermark, no extra objects.

Minimalist Flat Vector Travel Poster

Premium minimalist flat-vector travel poster for {argument name="city name" default="[CITY_NAME]"}, 3:4 vertical format. Design an original, sophisticated travel poster that captures the authentic visual personality of [CITY_NAME]. The composition must feel purpose-built for this city rather than following a reusable template. CITY IDENTITY First interpret the unique visual character of [CITY_NAME] and build the scene around these five elements: 1. A recognizable landmark, architectural feature, or skyline element. 2. A distinctive local way of moving through the city. 3. One subtle everyday lifestyle moment. 4. A native plant, landscape, or environmental characteristic. 5. A composition and viewpoint that naturally belongs to the city. The overall scene structure must change from city to city. Do not repeatedly use the same object positions or visual formula. Possible compositions include: harbor viewpoint, narrow historic lane, riverside garden, coastal path, elevated city overlook, lively market passage, tram avenue, ferry terminal, botanical setting, heritage square, beach promenade, cultural plaza, or skyline terrace. Choose whichever composition best represents [CITY_NAME]. TYPOGRAPHY Place “[CITY_NAME]” in the upper-left area with generous clean negative space. Add one short, sophisticated English tagline inspired by the atmosphere of the city. Typography should feel understated, editorial, spacious, and premium. Never allow text to dominate the artwork. VISUAL HIERARCHY Use one iconic landmark or architectural feature as the main focal point. Support it with only 2–4 carefully selected local elements. Every added detail should strengthen the sense of place. Avoid landmark collections or postcard-style collages. Keep the scene visually quiet and intentional. PEOPLE Include only 3–6 small-scale figures. Give each person a believable activity connected to local life, such as: walking through a historic lane, cycling, waiting for public transport, sketching architecture, boarding a ferry, reading outdoors, taking a quiet photograph, carrying beach equipment, browsing a market, or jogging beside the water. Avoid crowds and avoid making any single person the main character. Figures should integrate naturally into the environment. LOCAL CHARACTER Use city-specific elements only when they genuinely fit [CITY_NAME]: - local transportation - architecture - street furniture - vegetation - small signs or wayfinding - local food references - recreational activities - pavement markings - cultural details Transport and signage should remain subtle. Instead of always using a large signboard, incorporate details naturally through a small transit marker, station clock, ferry information panel, bike symbol, painted road marking, beach flag, or understated metro icon. ART DIRECTION Japanese stationery-inspired aesthetic, luxury sticker illustration, premium commercial vector artwork, modern editorial travel branding, clean delica

Train Mirror Selfie Fashion Portrait

Create a tall vertical photorealistic fashion portrait of a {argument name="subject" default="young adult woman"} sitting on a purple speckled bench seat inside a commuter train, taking a mirror selfie with a smartphone. She is framed full-body from a slightly high front angle, seated near the left wall of the train with a window on the right and beige metal interior panels behind her. Her face is partially hidden by a black smartphone with a quilted case and multiple rear cameras, covering the lower half of her face while her large eyes look directly toward the mirror/camera. She has {argument name="hair color and style" default="long wavy black hair with soft bangs"}; one hand holds the phone and the other lightly touches a lock of hair beside her face. She wears a Japanese school-uniform-inspired outfit with exactly 6 main visible clothing/accessory items: a beige cardigan, a white collared shirt, a navy plaid bow tie, a navy plaid pleated skirt, black thigh-high socks, and black loafers. A large black rectangular school bag rests across her lap, with one small round pink charm hanging from a silver keychain. The train seat is deep purple with a mottled texture, the floor is beige, the window shows a softly blurred outdoor scene, and the lighting is natural daylight, candid, realistic, slightly soft, with authentic phone-selfie composition and no text or watermark.

Seaside Sunset Portrait

Ultra-realistic iPhone photograph taken by the {argument name="setting" default="seaside during sunset"}. A {argument name="subject" default="handsome Korean young man"} is sitting naturally on a large coastal rock, captured from slightly to the side in a waist-up composition. His soft dark hair reaches his ears and gently blows in the ocean breeze, with a few strands falling across his face. He has smooth light warm-toned skin, delicate Korean facial features, straight brows, soft lips, and a calm, peaceful expression with a subtle smile. He is wearing a {argument name="clothing" default="relaxed white linen button-up shirt"} with a few top buttons undone, loose light gray-blue wide-leg trousers, and gray Nike Dunk sneakers. His physique is lean and athletic with broad shoulders and a slim waist. Around his neck is a delicate silver necklace with the letter "N" surrounded by small diamonds. The background features a calm gray-blue sea and a glowing golden sunset reflecting softly on the water. He is looking slightly toward the camera instead of directly at it, creating a candid atmosphere. His face is perfectly visible and sharply focused. Natural skin texture, realistic details, soft cinematic lighting, gentle wind movement, authentic iPhone photography aesthetic, ultra-photorealistic, high detail, serene mood, shallow depth of field, editorial lifestyle photography.

Luxury Emerald Green Product Photography

A luxury commercial product photography shot featuring a sleek {argument name="bottle color" default="matte emerald green"} glass bottle with a tall cylindrical neck, rounded shoulders, and a premium brushed gold cap. The fictional brand name {argument name="brand name" default="VERDARA"} is elegantly printed in embossed gold typography with a minimalist botanical emblem. The bottle is centered against a rich emerald green textured paper backdrop. The paper is dramatically torn open across the middle, revealing an overflowing bed of fresh green grapes, sliced kiwi, mint leaves, and sparkling lime wedges hidden beneath. A curled section of torn paper on the lower left adds depth and realism. Several fruits are scattered naturally across the foreground. Elegant editorial typography appears in the upper left: “{argument name="slogan" default="Sip Into Pure Freshness"}” “Sip” in modern handwritten brush script, “Into Pure Freshness” in sophisticated high-fashion serif typography. The bottle label features premium botanical illustrations of kiwi, grapes, mint, and lime with subtle metallic foil accents. Hyper-realistic glass reflections, natural condensation droplets, premium studio lighting, soft shadows, vibrant colors, razor-sharp focus, luxury beverage advertisement, photorealistic, ultra-detailed, award-winning commercial product photography, minimalist composition, 8K.

Cinematic Beach Walk with Flash

Ultra-realistic smartphone photograph of a {argument name="subject" default="woman"} walking along a {argument name="setting" default="secluded beach"} at dusk, captured in a vertical frame with an on-camera flash that creates the look of an authentic, spur-of-the-moment snapshot. The scene takes place beside the shoreline as the last traces of a deep crimson sunset fade into an almost black night sky. Behind her, dark ocean waves roll onto the sand, leaving bright white foam illuminated by the flash. The setting has a moody coastal atmosphere with cool sea breeze, subtle motion, and the feeling of an unplanned evening moment. A strong gust of wind sweeps her exceptionally long hair dramatically across her face, with loose strands obscuring part of her features. She instinctively lifts one hand to move the hair aside while continuing to walk, creating a candid sense of movement rather than a posed fashion shoot. Her facial details remain softly blurred by motion and wind, adding realism and mystery. She wears a {argument name="outfit" default="flowing black maxi dress"} with delicate spaghetti straps that moves naturally with the breeze, accentuating a graceful hourglass silhouette. High-detail textures, realistic flash reflections, natural skin tones, subtle motion blur, cinematic coastal lighting, authentic smartphone photography, premium lifestyle editorial aesthetic.

Japanese AI Training Banner

Create a sleek Japanese corporate training banner in a wide horizontal web-ad format with a dark navy-to-deep-blue gradient background, subtle glowing network nodes and connecting lines across the upper and middle area, and a high-tech AI/business atmosphere. Place a confident businessman on the right side from waist-up, wearing a dark navy suit, white dress shirt, and blue striped tie, arms crossed, facing forward; crop him partially at the top and right edge. On the left, create a strong typographic hierarchy with a small cyan headline at the top reading {argument name="headline text" default="AIを活用した開発スキルを、最短で習得"}, then an oversized bold white main title reading {argument name="main title" default="ClaudeCode研修"}. Along the lower-left area, place exactly 3 rounded rectangular feature boxes outlined in bright cyan with dark interiors and cyan icons: box 1 shows a terminal/code icon and the text "Claude Codeの基本と応用", box 2 shows a rocket icon and the text "開発スピードを飛躍的に向上", box 3 shows a two-person/team icon and the text "現場ですぐに活かせるスキル". On the far right, overlay a large cyan angled polygon callout panel with bold dark text in 2 lines reading {argument name="callout text" default="明日からの開発が\n変わる体験を。"}. Use crisp modern sans-serif Japanese typography, strong contrast, polished marketing design, clean spacing, luminous cyan accents, and a premium AI seminar advertisement look.

Futuristic Void Fang Mech

Mine pulses red beneath a {argument name="shell color" default="black shell"}. {argument name="model id" default="JFC-01"}｜{argument name="name" default="VOID FANG"}

Game of Thrones Isometric Map Diorama

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.

Isometric France Diorama Poster

Create a polished isometric country diorama poster for {argument name="country name" default="France"} in a premium travel-atlas style. Use a vertical 4:5 canvas on a warm off-white background, with the country shown as a thick floating 3D terrain cutout in its real recognizable outline, including the separate island of Corsica as a smaller detached cutout at lower right. The landmass should have steep rocky vertical edges, soft studio shadows, and an isometric camera angle looking down from above. At the top, add clean centered typography: small spaced uppercase region label "EUROPE", then a huge bold condensed uppercase title "{argument name="country title" default="FRANCE"}" in dark charcoal, with a simple vertical tricolor flag to the right of the title using blue, white, and red. Beneath the title, add a small spaced subtitle reading "{argument name="capital and population" default="PARIS • 67.4 MILLION"}". The diorama should be densely detailed: green countryside, patchwork farms, forests, rivers, roads, rail-like lines, villages, towns, harbors, coastline, and mountain ranges. Include exactly 10 prominent landmark or terrain features distributed across the map: 1 central Eiffel Tower near Paris, 1 large Gothic cathedral in the northeast, 1 domed monument in the west, 1 tall cathedral or basilica in the southwest interior, 1 white coastal lighthouse on the Atlantic side, 1 Mediterranean harbor with boats along the south coast, 1 snowy mountain range across the southeast Alps, 1 snowy mountain range across the southwest Pyrenees, 1 major winding blue river running north-south through the center-east, and 1 detached Corsica island with miniature towns and green hills. Add small boats and sailboats on the surrounding blue water, especially near the Atlantic coast and Mediterranean bay. Visual style: highly detailed miniature model, realistic 3D render, crisp topographic relief, vibrant natural greens and yellows, tiny architecture, clean editorial poster composition, soft ambient occlusion, subtle depth of field, no border, no watermark. Keep the overall image balanced with the text occupying the upper quarter and the isometric map filling the lower three quarters.

Kashmir Luxury Rain Masterpiece

Create an ultra-luxury cinematic masterpiece set on the {argument name="location" default="shores of Dal Lake, Kashmir"} during a dramatic rainy evening. A breathtakingly beautiful woman wearing an elegant {argument name="outfit" default="black velvet royal gown with intricate gold embroidery"} stands on a wet wooden promenade beside the lake, looking back with a confident expression. Majestic snow-covered Himalayan mountains rise in the background beneath dark storm clouds. Warm golden lanterns illuminate the scene, their reflections shimmering across the rain-soaked floor. A {argument name="car" default="vintage Rolls-Royce"} is parked nearby, adding a billionaire lifestyle aesthetic. Traditional Kashmiri houseboats glow softly across the lake, surrounded by mist and atmospheric fog. Ultra-realistic facial details, flowing fabric physics, glossy reflections, luxury fashion editorial photography, dramatic cinematic lighting, volumetric fog, shallow depth of field, premium color grading, black and gold luxury palette, photorealistic textures, masterpiece composition, hyper-detailed environment, Vogue magazine quality, Hollywood movie poster aesthetics, emotional storytelling, royal elegance, dark luxury atmosphere, 8K HDR, Unreal Engine quality, award-winning luxury advertising campaign, no text, no watermark, no logo, perfect symmetry, viral social media masterpiece.

Anime Girl Sketch by the Sea

Lighthearted sketch-style anime aesthetic, A serene, anime-inspired illustration of a {argument name="subject" default="young woman"} sitting against a tree by the seaside, full-body seated view at eye level, slightly turned three-quarter pose, looking down as she draws in a spiral sketchbook with a black pen. Soft pastel color palette with clean line art and gentle watercolor shading, warm, soft directional sunlight casting subtle, long shadows. She wears a {argument name="outfit" default="lavender long-sleeve blouse under a green pinafore dress patterned with small white daisies"}, a white underskirt with larger daisy prints peeking out, white ankle socks and brown loafers. Long dark hair, natural expression, light blush on cheeks. Large tree trunk with textured bark and {argument name="leaves" default="golden autumn leaves"} drifting in a light breeze; a few leaves scattered on the pavement. Background: calm blue ocean with gentle waves, pale sandy beach, distant horizon and soft fluffy clouds, a quiet two-lane coastal road beside the beach. Foreground includes a woven straw tote bag with colorful horizontal stripes placed on the curb. Emphasize peaceful, nostalgic mood, delicate details (fabric folds, leaf veins, bark texture, woven bag weave, pen and paper strokes), cinematic composition, high-resolution, soft grain, subtle rim light and natural ambient occlusion.

Lolita Maid With Anime Wall Sketch

Create a photorealistic editorial fashion image with an anime sketch transformation theme. A young woman with {argument name="hair color" default="light brown"} hair stands in the left third of the frame against a plain warm beige interior wall, wearing a black-and-white gothic lolita maid outfit: black puff-sleeve lace dress, white frilly apron, white lace cuffs, small white ruffled maid headband, white knee-high socks, and black Mary Jane platform heels. She poses shyly and slightly pouty, leaning near the corner with one hand resting against her cheek, the other arm folded, one leg straight and the other bent backward at the knee. To her right, drawn directly on the wall, show one large black ink manga/anime line-art version of the same maid character, about twice as dynamic and playful: winking, smiling with an open mouth, making a V-sign near her eye, one leg kicked up, apron and skirt fluttering, long hair flowing. Surround the sketch with exactly 8 doodle elements: 3 hearts, 3 stars, and 2 short emphasis marks. Use warm natural sunlight from a window on the left, casting diagonal shadows across the wall and wooden floor. Keep the composition split between real model on the left and hand-drawn anime alter ego on the right, with realistic photography texture, soft shadows, beige wall, baseboard, and parquet wood floor. No captions, no watermark, no extra characters.

Cinematic Moment of Fate Re-creation

Analyze the narrative of this illustration and identify the single most critical moment of fate within the story. [Scene Construction] - Recreate that decisive moment as a new illustration - The scene should feel candid and unposed — as if captured accidentally by a camera - The subject is caught mid-action, unaware of being observed - The composition is slightly off-balance, as if the photographer moved suddenly [Depth & Lens] - Place an out-of-focus object in the foreground close to the lens — a branch, fabric, foliage, architectural element, or any environmental object native to the scene - Human hands or body parts must never appear in the foreground - This foreground element creates strong depth separation - Apply shallow depth of field: the focal point is sharp, everything else falls into natural bokeh - Slight motion blur on peripheral elements suggests a fleeting moment [Imperfection] - The framing is imperfect — subject may be slightly off-center or partially cropped - Focus is not perfectly locked — the sharpest point is close but not clinical - The image feels like it was taken one second before or after the "perfect" shot [Atmosphere] - The emotional weight of the story's turning point must be felt in the image - Light and shadow reflect the tension of the moment - Preserve the original art style and color palette of the source illustration

Clear Glasses Smartphone Selfie Portrait

Create a realistic vertical smartphone selfie portrait of {argument name="subject" default="an adult East Asian woman"} in an extremely tight close-up, showing mainly the face, shoulders, and upper chest. She has {argument name="hair style" default="shoulder-length black hair with wispy bangs and one thin side braid"}, clear luminous skin, soft glossy pink lips, and large dark eyes looking directly into the camera. She wears {argument name="glasses" default="transparent amber rectangular eyeglasses"} lowered slightly on her nose, and lightly touches the outer edge of the frame with one index finger while resting her hand against her cheek. Her expression is calm, relaxed, slightly playful, and intimate. Dress her in an oversized {argument name="sweatshirt color" default="pale powder-blue"} crewneck sweatshirt with long ribbed cuffs pulled over part of the hand; include partial black printed lettering cropped at the bottom. Use a plain cool gray wall background, natural window light from the upper left, soft shadows, realistic skin texture, subtle hair flyaways, clear glass reflections, shallow depth of field, and a casual lifestyle cover-photo feeling. Composition should feel like a handheld phone selfie from slightly above eye level, portrait orientation 9:16, face filling most of the frame, no extra people, no watermark, no added text beyond the partial sweatshirt print.

Doodle Character Editorial Lifestyle Poster

同样处理： 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，使其具有生活方式杂志、独立出版物和艺术摄影质感。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。 下半部分先理解原图真正的**视觉核心与寓意**：判断画面最重要的不是“有什么”，而是“什么最值得被记住”——可能是一个主体、一种动作、一组关系、一处反差、一个情绪瞬间或某种象征意味。再从中提取最具识别性的**主体、轮廓、姿态与叙事线索**，重构为“真实主体 + 黑线涂鸦小人”的趣味编辑海报。不要机械截取原图最大物体，而要保留最能代表照片精神和故事性的视觉锚点，使下半部分既能一眼对应原图，又像对原图进行了一次聪明的二次解读。 真实主体保持材质与身份特征，可适度优化角度、比例、光线和色彩，使核心特征更鲜明；原图中与寓意无关的信息可以舍弃，但支撑主题的关键关系必须保留。围绕主体加入少量极简黑线涂鸦小人，小人的动作、位置和互动方式完全根据原图的形态、语境与潜在寓意自然生成，让他们像在回应、放大或反转照片原本的故事，而不是随意做动作。 配色从上方照片中提取最有辨识度和精气神的颜色，可适度提纯、提亮和重新组织。背景以米白、浅色或原图中最舒适的浅色为主，保持大量留白；真实主体承担主要色彩，小人与文字以黑色或深灰细线形成对比，整体干净、轻快、克制。 文字同样从原图的**核心寓意、情绪和视觉关系**中自然生长，不直接说明物体名称，也不套固定文案。将照片最值得被记住的那层意思转化成极短、轻松、聪明、略带幽默或双关的手写文字，让它像小人留下的注释、念头或一句画外音。文字可沿主体轮廓、人物动作或留白节奏自由排布，与小人和主体共同完成叙事，而不是后期贴上的标题。 整体保持**真实主体、核心寓意、微型叙事、稚拙线条和大量留白**之间的平衡。无论原图是人物、动物、植物、食物、建筑、器物、交通工具或自然场景，都应先抓住“这张照片真正讲的是什么”，再决定如何重构，避免只抓物体不抓关系、只做可爱互动没有主题、卡通贴纸感、复杂装饰和模板感。 💣language：{argument name="language" default="english"}

Attack on Titan Isometric Diorama Map

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.

Six VTuber Japanese Logo Sheet

Goal: Create a clean presentation sheet of exactly 6 original VTuber-style Japanese name logos on a white background, arranged in a 3-column by 2-row grid with generous spacing. Each logo should be a polished vector-like typographic mark with decorative motifs, glossy gradients, small romanized subtitle text, and no extra captions outside the logos. Canvas: Wide horizontal canvas, about 1200×690 px, pure white background, centered composition, high-resolution crisp edges, transparent-logo-design feeling but displayed on white. Layout: Exactly 6 discrete logos: 1. Top left: {argument name="top left name" default="月詠こよみ"} with small romanization “TSUKUYOMI KOYOMI”. Elegant deep navy Japanese calligraphy, crescent moon sweep in pale gold, dangling star charms, small flowers, sparkles, and a black cat silhouette sitting on the lettering. 2. Top center: {argument name="top center name" default="夢羽ころん"} with small romanization “YUMEHA CORON”. Cute pastel magical-girl logo in pink, lavender, and sky blue, rounded bubbly letters, fluffy cloud outline, tiny angel wings, halo above, stars, dotted lace border, and a pink bow at the bottom. 3. Top right: {argument name="top right name" default="黒燐アリア"} with small romanization “KOKURIN ARIA”. Gothic dark fantasy logo, black and crimson Japanese typography, thorny bat-wing flourishes, red rose crown at the top, diamond jewel shapes, rose petals, sharp spikes, and dramatic black ink accents. 4. Bottom left: {argument name="bottom left name" default="水瀬なぎさ"} with small romanization “MINASE NAGISA”. Fresh aquatic logo in turquoise and aqua gradients with pale gold accents, flowing wave underline, bubbles, seashells, small star sparkles, airy elegant rounded Japanese lettering. 5. Bottom center: {argument name="bottom center name" default="夜乃書ラウ"} with small romanization “YORUNOSHO RAU”. Dark academia midnight logo in deep navy and gold, large blocky Japanese lettering on a shield/book-shaped plaque, open book silhouette at the bottom, ornate golden frame, dangling stars, crescent/lantern-like ornament above, refined fantasy library mood. 6. Bottom right: {argument name="bottom right name" default="雷ヶ咲うた"} with small romanization “IKAZUCHI UTA”. Energetic pop-rock electric logo with bold black and white Japanese lettering, cyan and hot pink accents, lightning bolts, jagged comic effects, stars, checker/halftone details, small gamepad icon with X buttons, dynamic tilted rhythm. Visual style: Modern Japanese VTuber logo design, professional esports/idol branding quality, highly legible stylized kanji/kana, layered outlines, gradients, sparkles, ornaments integrated into each logo, crisp vector illustration, balanced colors, no mockup shadows, no watermark. Constraints: Use exactly 6 logos and exactly the 6 themes listed above. Keep the grid clean and evenly spaced. Preserve the Japanese text and romanized subtitles as part of each logo. Avoid photorealism, characters, people, UI panels, or extra explanatory text.

Blue Moonlit Sari Portrait

Create a low-key nocturnal vertical portrait of {argument name="character description" default="a young South Asian woman"} from upper torso to head, centered slightly below the upper half of the frame, with a huge luminous full moon directly behind her head like a halo. She has long loose wavy {argument name="hair color" default="black hair"} parted near the center, a calm introspective expression, her complete face visible, eyes looking down and slightly to her left, soft lips, and a small nose ring. Use a monochromatic cool-blue moonlit color grade with deep navy shadows, subtle rim light on the hair and shoulders, and smooth realistic photographic skin texture. She wears a dark navy sari draped diagonally over one shoulder and a matching short-sleeve blouse with a wide neckline. Include exactly three visible tattoos: two symmetrical black leafy branch tattoos across the left and right collarbones, and one small centered chest text tattoo reading {argument name="chest tattoo text" default="FEEL ME"}. The background is almost black with faint star specks and negative space, while the oversized moon is softly detailed with craters and a blue glow. Mood should be quiet, cinematic, mysterious, and romantic, with shallow depth of field, high contrast, soft moon haze, no extra people, no added text besides the tattoo, no watermark, and a polished editorial portrait style.

Isekai Guild Receptionist Character Transform

参照画像のキャラクターをベースデザインとして使用して、「{argument name="シーン" default="転生したアニメキャラクターが、異世界の冒険者ギルドで普通に受付嬢として働いている瞬間"}」を描く。キャラクターのアニメイラストとしての空気感を正確に維持する。キャラクターの顔、髪型、髪色、瞳、耳、シルエット、頭身、表情の印象を維持すること。キャラクターのアイデンティティを絶対に崩さない。別人化しない。実写人間化しない。キャラクター部分はアニメイラスト表現を維持する。舞台は{argument name="場所" default="異世界ファンタジー世界の大都市ギルド本部"}。背景は{argument name="背景エンジン" default="Unreal Engine 5"}で描かれたような高品質なファンタジー空間。リアル寄りの背景描写。生活感のある異世界空間。綺麗すぎない。コンセプトアート化しない。ゲーム公式ビジュアルのようにしない。背景には、巨大なクエスト掲示板、木製カウンター、依頼書、地図、武器ラック、革鎧の冒険者、魔導ランタン、石造りの壁、酒場スペース、吹き抜け構造、二階回廊、荷物、樽、雑多な備品などを自然に配置する。構図は一人称視点（POV）。視聴者はギルドを訪れた冒険者。画面手前には、冒険者の腕、手、依頼書、冒険者カード、報酬袋、地図、飲み物、荷物などを自然にフレームインさせる。POV側の人物は、・依頼書を受け取ろうとしている・冒険者カードを差し出している・報酬袋へ手を伸ばしている・地図を覗き込んでいる・受付カウンターへ寄りかかっているなど、受付とのやり取りが成立する自然な行動を取る。ギルド受付嬢となったアニメキャラクターは、・依頼書を差し出している・地図を広げて説明している・冒険者カードを返却している・報酬袋を渡している・初心者向けクエストを案内している・ランクアップを祝福している・少し眠そうに受付している・慣れた様子で業務をこなしているなど、「普通に働いている」自然な動作を行っている。重要：キャラクター本人は、異世界の受付嬢であることを特別視していない。周囲の冒険者達も、それを当たり前の日常として受け入れている。ゲームUI風オーバーレイを追加する。冒険者ランク、クエスト情報、所持金、パーティ情報、通知表示、ミニマップなどを自然に表示する。UI内容は固定しない。AI側が自然に生成すること。UIは主役ではない。受付嬢と冒険者のやり取りを補強する程度に留める。異世界とアニメキャラクターが自然に融合した、奇妙にリアルな空気感を重視する。映画ポスター風にしない。過剰なシネマティック演出禁止。綺麗すぎる構図禁止。AI特有の glossy rendering を避ける。情報量を盛りすぎない。「RPGのイベントシーンのスクリーンショット」ではなく、「異世界の日常を偶然目撃した一瞬」のような生活感と偶然性を重視する。high quality anime character, UE5 fantasy environment, POV shot, guild receptionist, natural interaction, fantasy daily life, weirdly realistic atmosphere

Kawaii Arcade Claw Machine Portrait

Hyperrealistic photograph in Japanese kawaii style. The beautiful young woman in the attached image sits inside {argument name="setting" default="a UFO Catcher arcade machine overflowing with Pokémon plushies"}. The composition is perfectly centered and symmetrical. The model holds the metal shaft of the claw above her head, her expression {argument name="mood" default="soft and melancholic"} as she gazes directly at the camera. She has long, wavy, dark brown hair, luminous and delicate skin, and her legs are elegantly extended atop a mountain of adorable plushies. The interior is completely filled with Pokémon plushies. The Japanese arcade machine is decorated with kawaii illustrations, Japanese typography, stars, hearts, and other cute details. {argument name="lighting" default="Enveloping neon pink LED lighting"}, vertical light tubes on both sides, cinematic reflections on glass and metal, soft bloom, dreamcore atmosphere, Harajuku aesthetic, pastel vaporwave, monochromatic cotton candy pink color grading, soft magenta tones, ultra-detailed, hyper-realistic, moderate depth of field, perfect focus on the model, realistic reflections, luxury editorial photography, Japanese magazine style, magical and nostalgic atmosphere, 85mm, f/2.0, HDR, 8K, masterpiece, ultra-realistic, cinematic lighting, premium fashion photography, highly detailed, soft glow, dreamy atmosphere.

Magical Sunrise Alpine Valley

Create a cinematic, ultra-realistic nature landscape at magical sunrise: a pristine alpine valley with a shallow winding river in the foreground, framed by dense evergreen pine forests and jagged snow-dusted mountain peaks in the background. The sun is low on the left horizon, casting warm golden light, long rays, glowing mist, and soft volumetric fog through the trees and across the valley. In the river, show exactly 4 spotted deer drinking or grazing at the water’s edge: three grouped near the center with heads lowered, and one smaller deer farther right near the riverbank. The foreground is filled with vibrant wildflowers, especially purple lupines and small yellow blossoms, with lush green grasses, stones, and river rocks. Use {argument name="time of day" default="golden sunrise"}, {argument name="main animals" default="four spotted deer"}, {argument name="mountain style" default="jagged alpine peaks with light snow"}, {argument name="flower colors" default="purple and yellow wildflowers"}, and {argument name="mood" default="magical, peaceful, cinematic"}. Make the composition wide and immersive, with strong depth from flowers in the foreground to river, forest, misty valley, and towering mountains. Photorealistic detail, natural colors, dramatic warm lighting, soft haze, high dynamic range, serene wilderness atmosphere, no text, no people, no buildings, no watermark.

Glossy AI Logo Redesign Row

Create a clean logo redesign showcase on a wide white canvas, featuring exactly 5 glossy rounded-square app icons evenly spaced in a single horizontal row, centered vertically with generous empty margins. Use a modern 3D glassmorphism style with soft shadows, subtle reflections, beveled edges, high saturation, and smooth gradient lighting. The five icons from left to right are: 1) a teal-to-mint rounded square containing a white interwoven knot emblem resembling the OpenAI logo, 2) a peach-to-orange rounded square containing a white radial sunburst or asterisk emblem with many tapered rays, 3) a cyan-blue-to-purple rounded square containing a large white four-point sparkle star plus one small sparkle near the upper right, 4) a black rounded square with deep blue highlights at the bottom containing a white lowercase-like geometric “k” mark and one small bright blue dot near the upper right, and 5) a lavender-to-purple rounded square containing a white outlined angular six-point star or badge emblem. Keep the composition minimal, polished, and product-design focused, with no text labels, no watermark, and no extra icons. The overall subject is {argument name="logo redesign theme" default="AI app logo redesigns"}, with {argument name="icon style" default="glossy 3D glassmorphism rounded-square app icons"}, on a {argument name="background color" default="pure white"} background.

Cute Sheep Girl Office Manga Page

{"type":"four-panel manga page","style":"soft pastel anime chibi, warm beige and cream palette, gentle morning light, rounded panel borders, clean readable Japanese dialogue, cozy comedic fantasy office slice-of-life","page":{"orientation":"vertical","panel_count":4,"gutter":"thin white spacing","border":"rounded brown outlines"},"setting":{"location":"small management office interior","details":["wooden floor","sunlit window","desk with papers","wooden chairs","bookshelves full of files and books","stacked boxes and office supplies","soft dust motes and sparkles in the light"]},"characters":[{"role":"main character","appearance":"tiny chibi sheep girl clerk with short fluffy blond bob hair, one blue eye and one amber eye, small elf-like ears, large curled ram horns, fluffy sheep hood shaped like a sheep face, white blouse, red necktie, pale pink apron dress, small pen in apron pocket"},{"role":"secondary character","appearance":"round fluffy white sheep with tiny face and short legs, very plush and cloud-like"}],"layout":{"sections":[{"title":"panel 1","position":"top","count":3,"labels":["sheep girl opening the office door and looking inside","small sheep peeking beside her","one oval speech bubble on the left and one small oval bubble on the right"]},{"title":"panel 2","position":"upper middle","count":3,"labels":["sheep girl standing by a desk with one hand on hip and one hand pointing to documents","small sheep sitting by the desk","single large oval speech bubble on the left"]},{"title":"panel 3","position":"lower middle","count":3,"labels":["sleeping fluffy sheep sprawled on top of paperwork","partial close-up of the sheep girl peeking in from the upper left with a tired expression","purple sleeping sound effect text on the right"]},{"title":"panel 4","position":"bottom","count":4,"labels":["sheep girl asleep at the desk with closed eyes and a faint smile","fluffy sheep sleeping beside her on the paperwork","warm sunlight streaming from the left window","small rectangular caption box at bottom right"]}]},"text":{"language":"Japanese","elements":[{"kind":"speech bubble","panel":1,"text":"管理人室、ここにしよう… ほわあ"},{"kind":"speech bubble","panel":1,"text":"メェ"},{"kind":"speech bubble","panel":2,"text":"おい、住民の名簿をまとめなさい"},{"kind":"speech bubble","panel":3,"text":"…名簿が もふもふに…"},{"kind":"sound effect","panel":3,"text":"Zzz…"},{"kind":"speech bubble","panel":4,"text":"あったかいから… まあいっか…"},{"kind":"caption","panel":4,"text":"{argument name="caption text" default="管理業務、進捗ゼロ"}"}]},"composition":"keep all four panels in the same office for continuity; emphasize cute facial expressions, fluffy textures, and the joke that office work stops because the sheep and clerk fall asleep together on the paperwork; make the documents clearly visible in panels 2 through 4; preserve a calm, sleepy, heartwarming tone"}

E-commerce Product Poster Transformation

帮我生成符合剃须刀这个品类风格的宣传图；背景换成深蓝色，更有科技感；文案改成'3D浮动刀头'；生成XX品类电商海报

54-fashion-editorial-description-using-goog

A full-body fashion editorial photograph of a woman standing indoors in a modern minimalist studio. She faces the camera with a calm, confident expression, standing in a relaxed pose with one hand gently resting on her waist and the other holding a small structured handbag. She wears a soft sage green long-sleeve satin blouse with subtle draping and a high neckline, paired with cream high-waisted tailored straight-leg trousers. Her outfit is elegant, modest, and refined. Her brown hair is styled in a loose low bun with soft face-framing strands, and she wears delicate pearl drop earrings. The room features a light neutral sofa, an arched wall opening, white sheer curtains, an indoor plant, a small round side table, and a visible studio softbox in the background. Soft natural light enters from the left side, creating gentle shadows and a warm atmosphere. Clean editorial fashion photography style, shallow depth of field, neutral tones, ultra-detailed, 8K, vertical portrait.

Extreme Worm's Eye View Portrait of Megan Fox

{ "technical_specifications": { "camera_angle": "Extreme Worm's Eye View (Low Angle)", "ca…

High-Fashion Denim Editorial with Dynamic Pose

{ "prompt": "Denim fashion editorial photography, young woman with long platinum white blonde wavy…

10+ Page Manga Creation Prompt

nanobanana proを使った10ページ超漫画作成プロンプト。

2x2 Grid Collage of Luxury Lifestyle Photos

{ "image_layout": "2x2 grid collage featuring four distinct photographs of the same female subject.", "subject_general": { "gender": "Female", "hair_color": "Dark brown/black", "hair_style": "Long, styled in loose waves in three panels; sleek high ponytail in one panel", "aesthetic": "Glamorous, influencer, trendy, luxury lifestyle" }, "panels": [ { "position": "top_left", "setting": "Outdoors at night, dark background with illuminated green foliage", "action": "Subject is holding a cake with one hand and licking frosting off the index finger of the other hand", "outfit": { "top": "Black halter-neck sleeveless top", "jewelry": "Gold wristwatch, gold bangle bracelet, ring, small hoop earrings" }, "props": { "item": "Round white frosted cake", "details": [ "Red cherries on top", "Decorative white piping along edges", "Black icing text reading '{argument name="cake text" default="bad bitch energy"}'" ] } }, { "position": "top_right", "setting": "Daytime city street, likely an upscale shopping district (e.g., Rodeo Drive) with palm trees and storefronts visible", "action": "Subject is leaning out of the open door of a black luxury car, looking at the camera", "outfit": { "top": "White sleeveless ribbed crop top", "bottom": "Blue denim jeans", "accessories": "Shoulder bag (strap visible), gold hoop earrings" }, "lighting": "Bright natural sunlight casting shadows" }, { "position": "bottom_left", "setting": "Indoor hallway, beige walls, wooden floor", "action": "Full-body mirror selfie", "outfit": { "style": "Matching two-piece set", "color": "Dark brown/chocolate", "top": "Velvet/suede corset-style bustier top", "bottom": "Mini skirt", "accessories": "Patterned designer handbag (resembling Dior Saddle bag), stack of gold bracelets" }, "background_details": [ "Large rectangular mirror with gold frame leaning against wall", "Vase with pampas grass in the corner", "Doorway visible in reflection" ] }, { "position": "bottom_right", "setting": "Inside a vehicle or outdoors, golden hour sunlight", "action": "Close-up selfie, hand raised near mouth/chin", "outfit": { "top": "Light pink/mauve ribbed tank top", "outerwear": "Beige fuzzy/sherpa jacket worn off-the-shoulder", "jewelry": "Layered gold necklaces with pendants, hoop earrings" }, "hair_styling": "Sleeked back high ponytail", "background_details": "Car window frame, palm trees and blue sky visible in background" } ] }

Rainy Hong Kong Schoolgirl Guitar Collage

cinematic photo collage · teenage Asian schoolgirl musician · black school blazer over a white dress shirt with a loose black tie · dark pleated plaid skirt · black knee-high socks · black loafers · dark brown to black · long straight hair with bangs, slightly messy from humidity and wind · black electric guitar, smartphone visible in selfie shots · small soft angel wings appearing in some shots, moody introspective expression · dense Hong Kong city streets and harborfront · rainy overcast evening · wet pavement, misty air, light drizzle · narrow urban streets, tall apartment and shop buildings, neon and shop signs with Chinese text, double-decker bus, traffic and headlights, waterfront skyline · smartphone snapshot realism mixed with cinematic memory-image tone · muted teal, brown, gray, and amber palette with slightly faded colors · natural cloudy light, dim urban glow, reflective wet surfaces · casual handheld phone photography, imperfect framing, slight motion blur, shallow to medium depth of field · nostalgic, melancholic, urban youth music video interlude · rounded-corner 12-photo collage in a 3-column by 4-row grid · 12 · top row · row 1 · 3 · rainy Hong Kong intersection with tram tracks and tall buildings, girl seen through a train or tram window with reflections and motion blur, mirror selfie of the girl indoors holding phone while wearing guitar and soft angel wings · second row · row 2 · 3 · close-up of her legs and loafers on wet street markings, rooftop or elevated city view with her hair at frame edge and hazy skyline, close-up of hands playing black electric guitar · third row · row 3 · 3 · girl standing in front of a convenience store or vending refrigerator at night, cafe table with cup and saucer, smartphone, and small metal sugar pot, harbor water and distant skyline with her hair blowing across the frame · bottom row · row 4 · 3 · full-body rainy street shot of the girl carrying the guitar with wings faintly visible, portrait behind a rain-streaked window or glass panel with condensation, wet city street with a lone figure and blurred traffic lights receding into the distance · the recurring schoolgirl guitarist as if documented over one rainy day in Hong Kong · Create a 12-image collage that feels like {argument name="character name" default="an unnamed schoolgirl guitarist"} casually photographed these moments on her smartphone while wandering through {argument name="city" default="Hong Kong"}. The collage should look like intimate, accidental snapshots and memory fragments rather than polished commercial photography. Include exactly 12 images in a rounded-corner 3x4 grid, each frame slightly different in composition and distance, showing rainy streets, transit reflections, a mirror selfie with black electric guitar, close-ups of shoes, guitar hands, cafe table details, convenience store glass, harbor skyline, and rain-soaked urban night scenes. The girl wears {argument name="outfit style" default="a black school uniform blazer, white shirt, black tie, plaid skirt, knee-high socks, and loafers"}, with {argument name="hair style" default="long dark hair with bangs"}. Add subtle {argument name="fantasy element" default="angel wings"} in some frames only, blending dreaminess into realism. Emphasize handheld phone imperfection, slight blur, reflections, off-center framing, damp atmosphere, muted cinematic grading, and the feeling of a scene that could be inserted into a music video interlude.

Mecha Character Concept Showcase

Create a high-end, asymmetric editorial CHARACTER CONCEPT SHOWCASE from these inputs: [STYLE]: {argument name="art style" default="stylized 3D cinematic sci-fi anime / high-detail Gundam-inspired mecha concept art"}, with crisp mechanical panel lining, clean decals, and atmospheric lighting

Ultra-Realistic FMCG Product Ad Shot Prompt

Ultra-realistic commercial FMCG photography showing a {argument name="brand name" default="BRAND_NAME"} {argument name="product type" default="PRODUCT_TYPE"} revealed or opened at the bottom center of the frame. The product bursts upward in frozen mid-air motion. Dynamic splashes, pours, fragments, or particles related to {argument name="variant" default="VARIANT"} explode around it. Fresh {argument name="key ingredient" default="KEY_INGREDIENT"} elements appear whole and cut, suspended naturally with fine particles. The {argument name="brand name" default="BRAND_NAME"} logo and “{argument name="variant" default="VARIANT"}” text are clearly readable on realistic packaging with authentic material texture. Gradient background inspired by the variant. Dramatic studio lighting. Ultra-sharp focus. Premium cinematic advertising realism. 8K quality. 3:4 aspect ratio.

High-End Cocktail Visual Marketing Prompt

A high-end studio photograph of a [{argument name="cocktail name" default="YOUR COCKTAIL"}], shot from a high-angle slightly top-down perspective. The drink is served in its appropriate traditional glass with an elegant design and professional garnish. Artfully scattered around the base of the glass are fresh fruits and ingredients associated with the cocktail recipe. The scene features a warm, summery atmosphere with a light orange-tinted background. Artistic soft shadows of tropical palm leaves are cast across the frame, creating a vacation vibe. Realistic condensation on the glass, soft golden hour lighting, 8k resolution, professional food photography, sharp focus, clean and sophisticated composition.

Epic Fantasy Warrior Landscape

An epic fantasy landscape digital illustration featuring a {argument name="subject" default="solitary hooded warrior"} standing atop a rocky outcrop, gazing toward a {argument name="landmark" default="distant medieval castle"}. The figure is rendered in silhouette, wearing dark leather armor and a flowing hooded cloak. They grip a longsword in one hand and hold aloft a glowing lantern with warm amber-orange light in the other, creating a striking contrast against the cool tones of the environment. The landscape is dominated by a breathtaking mountainous vista with: Towering rocky cliffs rising dramatically on both sides, creating a natural amphitheater A grand Gothic castle perched majestically atop a distant cliff, with multiple spires and towers silhouetted against the sky A cascading waterfall visible in the misty background, adding movement and grandeur to the scene Dense coniferous forest of evergreen trees scattered across the mountainous terrain at various elevations Thick, atmospheric mist and fog swirling through the valleys and around the cliffs, creating depth and mystery Color palette and atmospheric elements: {argument name="color theme" default="Cool blue-teal color grading"}: Dominates the entire scene, creating a serene yet mysterious atmosphere Warm golden glow: The lantern provides a focal point of warmth and hope Dramatic cloudy sky: Overcast with hints of pale light, featuring silhouettes of birds in flight formation Volumetric lighting: Mist and fog particles catch light, creating atmospheric depth and dimension Monochromatic blues and teals: With touches of amber and earth tones Mood and thematic elements: Epic and cinematic: Reminiscent of fantasy films and video game concept art Adventurous yet contemplative: The lone figure suggests a hero's journey or quest Majestic and awe-inspiring: The scale of the landscape dwarfs the individual Mysterious and otherworldly: The mist and lighting create an almost dreamlike quality Hope and determination: The glowing lantern symbolizes perseverance in darkness Art style: High-quality digital fantasy illustration; concept art aesthetic with cinematic lighting and atmospheric effects; reminiscent of fantasy RPG artwork, Lord of the Rings-inspired visuals, or video game concept design

182-image-on-gemini-nano-banana

​A high-contrast double exposure photograph. The primary silhouette is the back of a man standing still, facing away from the camera. Inside his silhouette, a secondary scene is revealed: a narrow, war-torn city street at sunset. The street is lined with crumbling, hollowed-out concrete apartment buildings and scattered rubble. A smaller, lone figure walks down the center of the cracked road toward a bright, glowing sun on the horizon. The color palette is dominated by warm ambers, burnt oranges, and deep shadows, creating a somber yet hopeful atmosphere. Hyper-realistic textures, cinematic lighting, 8k resolution.

Cinematic Street Photography Editorial Portrait

Medium-up editorial portrait shot at eye-level, focusing on a man looking directly into the camera. He is standing in front of a grey textured stone building with an arched doorway in the background. The man is wearing a {argument name="coat type" default="[COAT]"}. Underneath, he wears a white dress shirt, a brown patterned tie, and a dark V-neck sweater. Accessories include a dark navy wool flat cap, gold- rimmed aviator sunglasses with brown lenses, and black leather gloves. His hands are tucked into the large side pockets of the coat. To the left, a vintage black outdoor lantern is mounted on the stone wall with dry vines climbing around it. Soft overcast natural lighting, cinematic street photography, high-end fashion editorial style, sharp focus on facial features and fabric textures, 8k resolution.

Nano Banana 2 prompt for creating figures and 3D models

Masterpiece, best quality, (product photography:1.6), macro lens, 8k resolution, (photorealistic:1.5). (Core Subject: High-End PVC Figure): The EXACT character from the input image is rendered as a (high-end 1/7 scale PVC figure:1.6). The figure stands on a clean wooden desk surface, out of the box. (Texture & Quality - CRITICAL): Premium matte plastic skin texture, glossy eye paint, intricate clothing folds, and precise airbrush shading. The figure looks like a tangible, expensive collector's item (Good Smile Company or Alter quality). A clear acrylic circular base supports the figure. (Background: 3D Workspace): Behind the figure, a computer monitor displays a (3D modeling software interface:1.5) (like Blender, Maya, or ZBrush). On the screen: A (grey wireframe mesh or untextured clay render:1.5) of the SAME character is visible. The screen represents the digital prototype of the physical figure. (Surroundings): The figure's retail packaging box stands vertically next to the figure, featuring the character art. A blurred mechanical keyboard and mouse are visible in the background. Soft, professional studio lighting illuminates the figure from above. (Technical Tags): (depth of field:1.4), (bokeh:1.3), (PVC texture:1.5), (figure photography:1.4), (ray tracing), sharp focus on figure face. (Negative prompt): (2D illustration:1.6), (anime style:1.5), (drawing), (sketch), (distorted face:1.5), (melted plastic), (bad painting), (messy desk), (screen off), (wrong character on screen), low quality, blurry.

Isometric Circular Museum Architecture

Create a clean isometric architectural concept rendering of a modern circular tiered building on a square site, in a minimalist white paper-model style. The main subject is a large round multi-level structure with exactly 5 visible stacked circular tiers: a wide ground floor ring, three progressively smaller upper rings with continuous narrow vertical window bands, and a top circular roof level. Add a small rectangular rooftop volume placed off-center on the top disk, and a wedge-shaped cut or recessed notch in the top roof edge. Attach two simple rectilinear annexes to the main building: one low rectangular wing extending to the right front, and one tall plain rectangular tower block at the rear right. Include one small separate circular pavilion near the front left of the building, connected by a short walkway. The site should be a square raised base with rounded road edges, pale gray paths, and soft green landscaping. Count the landscape elements clearly: exactly 9 small stylized trees or shrubs visible around the site, including 3 at the left green island, 2 small round shrubs at the front-left lawn, 1 tree near the front center, 1 shrub on the central lawn, 1 tree near the front-right curve, and 1 tree at the far right lawn. Use an orthographic isometric camera looking down from above, centered composition, lots of negative space, off-white background, subtle ambient occlusion, fine gray outline strokes, soft shadows, no people, no cars, no signage, no text. Color palette: warm white architecture, light gray pavement, muted sage green grass, delicate technical-illustration linework. Render as a polished architectural massing model, crisp and elegant, with simple geometry and smooth rounded forms.

Cozy Winter Lifestyle Brand Advertisement

A cozy winter lifestyle advertisement poster. A stylish young woman in a thick cream wool coat and knit scarf stomps happily beside a giant brown leather winter boot 3x her height with fur lining visible at the top, "{argument name="brand name" default="FROSTLINE"}" written on the boot sole in white. Magical snowy winter forest background with falling snowflakes and pine trees. Bold strong serif typography "{argument name="background text" default="FROSTLINE"}" in deep brown filling the background. Tagline bottom: "{argument name="tagline" default="Step into the cold, fearlessly."}" Small text top-right corner reads "Designed with GPT Image 2" in grey. Photorealistic, cozy winter fashion editorial, soft snowy blue white lighting.

79-style-transfer-with-nano-banana-pro

Create a grid of 4 different camera angles of [@]img1, [CAMERA ANGLE], that follow the same style and colour palette as [@]img1. Make the new shots unique.

Perler Beads Style Structural Poster

生成一张 16:9 横版信息图海报。 主题：【主题】 必须覆盖的知识点： 【知识点1】 【知识点2】 【知识点3】 【知识点4】 【知识点5】 【知识点6】 【知识点7】 【知识点8】 视觉风格定义： 这是一张“拼豆 / Perler beads / fuse beads / 像素珠阵列”风格的结构性平面信息图海报。画面由大量规则排列的圆形塑料拼豆构成，每一颗拼豆都具有清晰圆形边界、轻微中心凹点、均匀间距、低饱和塑料质感和稳定网格秩序。整体必须保持正视平面构图，像一张由拼豆拼成的公共文化信息图海报，而不是玩具摄影、3D模型、卡通插画或普通像素画。 核心构图： 将【主题】主体压缩为一个大尺度单色拼豆图像场，而不是完整写实物体、居中插画或图标集合。主体必须从画幅边缘涌入，跨越页面边界，并被出血裁切，像一个更大的拼豆媒介图像残片进入纸面。主体占据主要视觉重量，但不完整呈现；观众必须通过轮廓、方向、缺失区域、拼豆密度和局部纹理重建主题。 主体形态： 主体外缘呈现低分辨率拼豆台阶、方块断裂、硬切缺口、像素化锯齿轮廓、缺珠断面和被采样后的粗糙边界。禁止平滑剪影，禁止完整图标轮廓，禁止写实细节。主体内部只使用同一主题结构色的不同明度拼豆，形成低对比影像碎片、半调噪声、扫描颗粒、材料残影、档案纹理和局部密度变化。 背景与负空间： 背景使用高明度浅色拼豆底场，接近未印刷纸面、浅奶白塑料底板或淡灰白拼豆阵列。背景不是装饰底色，而是主动反向切入主体，形成大块空洞、曲折通道、安静文字窗口、阅读停顿区和知识点容器。空白必须像空气，也像刀口；它既提供呼吸感，也切割主体结构。大块浅色底与大块主题结构色必须互相侵入，不能简单上下分区，不能成为普通背景。 色彩系统： 采用严格的三层功能配色，不允许平均化配色。 第一层：浅色底场 面积比例约 60%–70%。功能是呼吸、切割、停顿、承载文字窗口。颜色可为旧纸白、浅米白、冷灰白、淡蓝白或淡暖灰。 第二层：主题结构色 面积比例约 25%–35%。功能是构成主体、制造空间压力、表达主题情绪和材料语义。颜色必须根据【主题】选择，例如冷主题可使用深蓝、墨绿、灰紫、石墨色；暖主题可使用赭红、土橙、棕黑、暗金色。结构色内部允许通过拼豆明度差表现颗粒密度和图像残影。 第三层：高对比信息色 面积比例约 3%–6%。功能是标题、编号、时间、注释、机构信息、图例、脚注和关键知识点标记。信息色必须少量、锐利、明确，可使用红、黑、亮蓝、荧光橙或高纯度青色。信息色不能扩散为装饰色。 信息图系统： 将【知识点1】至【知识点8】全部转化为拼豆信息节点，不使用普通图标堆叠解释。每个知识点以以下形式之一呈现： - 小型编号标签 - 微型注释框 - 拼豆图例块 - 坐标线 - 时间刻度 - 比例条 - 方向箭头 - 档案索引编号 - 局部纹理说明 - 边缘标记点 信息节点必须沿留白窗口、色场边界、切口节点、主体缺口、负空间通道和底部边缘分散布置。信息节点数量为 8 个，对应 8 个知识点。所有信息节点必须有层级关系：主标题最大，核心概念次级，知识点标签更小，脚注和编号最小。信息节点不能覆盖主体中心，不能破坏大色场结构。 阅读路线： 构建跳跃式阅读路径：上方小型标记 → 侧向主标题 → 主体边缘知识点 → 负空间注释窗口 → 底部脚注与图例。画面必须同时满足远距离识别和近距离阅读：远看是一个强烈的巨大拼豆图像残片，近看是一个精密、有秩序的知识信息系统。 字体与文字： 使用窄身现代无衬线字体、瑞士风格无衬线、方正清晰骨架字体或等宽元数据字体。字体笔画均匀，字距克制，层级精确。主标题像公共文化信息坐标，小字像档案元数据索引。文字必须排布在留白窗口、边界节点和底部信息栏中，不得压在主体中央。中文文字必须清晰、短句化、标签化，避免长段落。 主题转译规则： 不要直接用题材默认图标解释【主题】。必须把主题中的时间、地点、功能、人物关系、数据关系、因果关系或抽象概念转译为： - 拼豆色场密度 - 缺珠区域走向 - 边缘压力 - 负空间形状 - 信息节点位置 - 编号系统 - 局部纹理差异 - 拼豆明度层级 - 图例色块关系 拼豆材质： 所有视觉元素都由拼豆构成。拼豆表面为哑光塑料质感，带轻微制造不均、微弱颗粒、细小磨损和低对比表面差异。结构色区域内部可出现半调式拼豆密度变化、扫描输出感、旧纸不均匀感和专色叠印感。信息色拼豆必须边缘锐利、对比清楚、定位准确。 画面气质： 整体应像一张由拼豆重构的结构性公共文化信息海报。它不是可爱手工图，也不是儿童玩具风，而是克制、理性、现代、档案化、信息密集但秩序清晰的视觉系统。画面要有博物馆展览海报、研究机构信息图、公共文化导视和实验性平面设计的气质。 构图硬性要求： - 16:9 横版 - 正视平面视角 - 拼豆圆形颗粒清晰可见 - 主体从画幅边缘进入 - 主体被页面边界裁切 - 大块结构色与大块空白互相侵入 - 外轮廓呈拼豆像素台阶 - 至少 8 个知识点信息节点 - 远看有巨大图形冲击 - 近看有精密信息秩序 - 空白区域必须参与叙事和切割 - 信息色只能用于关键文字和标记 禁止内容： 禁止完整写实物体。 禁止居中主体插画。 禁止可爱卡通风。 禁止普通像素画。 禁止 3D 玩具摄影。 禁止景深虚化。 禁止真实相机拍摄感。 禁止强投影。 禁止发光特效。 禁止金属高光。 禁止复杂装饰背景。 禁止图标堆叠式信息图。 禁止平均分配颜色。 禁止文字覆盖主体中心。 禁止无意义信息噪声。 禁止把知识点变成随机装饰。 禁止过度拟物化。 禁止真实照片拼贴。 禁止渐变炫光。 禁止赛博霓虹背景。 禁止柔和插画风。 禁止水彩、油画、厚涂、3D渲染风。 最终效果： 画面应呈现为一张高级拼豆风格结构性信息图海报。【主题】不是被直接画出来，而是被压缩成巨大的拼豆色场、像素化珠阵边缘、缺珠空洞、负空间刀口、编号节点、档案注释和颗粒秩序。观众远距离看到强烈的抽象主题冲击，近距离能够沿信息节点阅读完整知识结构。 主题：潘金莲

Miniature Pet on Palm Prompt for Image Generation

사진 속 {argument name="동물" default="동물"}을 손바닥 위에 쏙 올라가는 미니어처 크기로 만들어줘. 위에서 아래로 내려다보는 구도로 잡고, 원본의 얼굴 특징과 표정은 왜곡 없이 그대로 유지해줘

Three Variations of a Blonde Woman in Black Clothing

{ "action": "image_generation", "action_input": "{ "prompt": "A high-quality, realistic full-body shot of a young woman with blonde hair and blue eyes, wearing a stylish black outfit. She is standing in a lush, sunlit garden surrounded by vibrant flowers and greenery. The lighting is soft and natural, creating a warm and inviting atmosphere. The composition is artistic and well-balanced, focusing on her serene expression and the beautiful outdoor setting." }", "thought": "The user wants to generate different images based on the provided photos. I will create a prompt that captures the essence of the woman's appearance (blonde hair, blue eyes) and her style (black clothing) but places her in a completely new, high-quality setting like a sunlit garden to provide a 'different' image as requested." } { "action": "image_generation", "action_input": "{ "prompt": "A cinematic, high-resolution portrait of a young woman with blonde hair and striking blue eyes. She is wearing an elegant black evening dress and is posed in a modern, minimalist urban rooftop setting during the golden hour. The city skyline is visible in the background with soft bokeh. The lighting is dramatic and warm, highlighting her features and the texture of the dress." }", "thought": "For the second variation, I'll change the environment to a modern urban rooftop at sunset. This maintains the character's core look but offers a different mood and background compared to the original indoor and hayfield settings." } { "action": "image_generation", "action_input": "{ "prompt": "A professional studio photography shot of a young woman with blonde hair tied in a bun and blue eyes. She is wearing a sleek, black athletic zip-up top. The background is a clean, neutral grey. The lighting is sharp and professional, emphasizing the contours of her face and the fit of the clothing. High detail, 8k resolution." }", "thought": "For the third image, I will focus on a studio setting that mirrors the 'selfie' style of the first image but elevates it to a professional photography level. This provides a clean, focused alternative while staying true to the visual elements found in the source images." }

Nano Banana - Rooftop Dinner Night

Luxury rooftop dinner in Paris at night with Eiffel Tower view. Woman seated at an elegant table full of candles, wearing a deep red satin dress, soft smile, wind gently moving hair.

Raw Chaotic Ink Poster Prompt

raw chaotic ink poster · face (use original reference only for proportions) · dense curved black scribble strokes · overlapping uneven lines · rough cross-hatching · slightly asymmetrical · minimal flat beige · solid flat orange · high contrast · false · false · false · none · formed with tangled overlapping strokes · irregular tangled aura surrounding the face

Photorealistic Full-Length Selfie with Identity Preservation (JSON)

image_generation_prompt · casual, modern, photorealistic selfie · vertical · full-length · mirror or selfie photograph · female · true · false · Preserve facial features, face structure, eye color, hairstyle, skin tone, and abdominal tattoos with maximum fidelity · serious and confident · holding a cell phone taking the photo · playing with hair · standing against a wall, facing the camera · dark · long · straight bangs with two long thick braids over the shoulders · dramatic · winged eyeliner, lipstick · abdomen · discreet but visible · black cropped top with red inverted text reading "I'M F***ING STAR" · short, tight denim shorts · necklace with heart pendant · dark or black · simple, minimalist · soft, diffuse frontal lighting · low · minimal, no harsh shadows · high-quality smartphone selfie · 24mm–35mm · f/1.8–f/2.0 · 200–400 · 1/125s–1/250s · soft bokeh despite wall background · remove any text overlays on the image such as 'hola' · photorealistic · high · natural skin and fabric detail · Create a realistic full-length selfie-style portrait that perfectly merges the user’s real identity with the described pose, outfit, hairstyle, lighting, and minimalist aesthetic.

National Team Jersey Fashion Portrait

一位{argument name="人物" default="成年女性足球宝贝"}穿着{argument name="服装" default="国家队配色的改良版修身球衣"}，上衣略短，搭配高腰运动短裙，造型时尚、清爽、带有适度的女性魅力，笑容热情，身体姿态自然舒展，手中抱着足球，背景是虚化的世界杯赛场和热烈欢呼的观众，光线明亮通透，画面既有运动感也有时尚写真感，高清写实，青春、吸睛、不过度暴露

Atmospheric Product Interface Visual Prompt for SaaS UI

Atmospheric product interface visual for a modern SaaS platform. Clean hierarchy, balanced contrast,…

Stunning Photo Prompt for Gemini Nano Banana

A majestic, armored dragon, scales shimmering with metallic iridescence, perched atop a jagged, snow-capped mountain peak. The dragon is bathed in the dramatic, golden light of a setting sun, casting long, sharp shadows. Its eyes glow with an inner fire. Cinematic composition, hyper-detailed, photorealistic, fantasy art, 8k, volumetric lighting, deep focus, dramatic atmosphere.

Romantic Weekend Getaway Poster

Design a romantic weekend getaway poster for {argument name="location" default="[CITY/REGION]"}, boutique hotel balcony, candlelit dinner, scenic street lights, soft warm color grade, elegant script typography, luxurious travel ad style.

Watercolor Illustration of Kittens in a Garden

A soft watercolor illustration of two adorable, fluffy kittens walking side-by-side in a flower garden. One kitten is a grey and white tabby, the other is ginger and white, both with large blue eyes. They are surrounded by pink daisies, blue wildflowers, tall grasses, and fluttering pink butterflies. The background is a dreamy blue sky with watercolor textures. Pastel color palette, wet-on-wet technique, paper texture, soft diffused lighting, whimsical and cute atmosphere.

JSON Prompt for Stylized 3D Character Render (Minimal Cartoon)

{ "task": "image_style_transfer_3d_character", "input": { "source_image": "USER_UPLOADED_IMAGE",…