Image2Studio
Prompts

gpt-image-2

桌面端 AI Agent 架构图

一份精美的中英双语企业级架构信息图，适用于演示文稿、产品规划或解释桌面端 AI Agent 系统的分层设计。

PosterUI MockupsInfographicssocial-media-postminimaleditorial
Generate with this prompt
Copy this GPT Image 2 prompt for social media post and infographics with Minimal, Editorial styling. Use it in Image2Studio to generate, edit, and save.
Copy this GPT Image 2 prompt for social media post and infographics with Minimal, Editorial styling. Use it in Image2Studio to generate, edit, and save.
Prompt

{"type":"bilingual enterprise architecture infographic","topic":"{argument name=\"headline text\" default=\"桌面端 AI Agent 架构图\"}","subtitle":"面向代码生成、项目协作与本地执行的 Desktop AI Agent Architecture","style":{"look":"clean modern SaaS diagram, corporate presentation slide, vector infographic","background":"very light gray-white","palette":{"primary":"deep navy blue","secondary":"medium blue","accent":"teal green","support":"soft gray","security":"bright royal blue"},"typography":"bold Chinese headline with smaller bilingual labels, crisp sans-serif, high legibility","icons":"minimal line icons inside rounded white cards with subtle shadows and blue outlines","geometry":"symmetrical grid, rounded rectangles, thin connector arrows, evenly spaced modules"},"layout":{"orientation":"landscape 4:3 presentation slide","header":{"title_centered":true,"title_size":"large","subtitle_below":true},"sections":[{"title":"可观测性","position":"far left vertical sidebar","count":4,"labels":["监控","Tracing","Metrics","错误告警"],"container":"tall rounded blue panel with four stacked cells and icons"},{"title":"安全治理","position":"far right vertical sidebar","count":4,"labels":["权限校验","敏感信息保护","命令确认","审计追踪"],"container":"tall rounded blue panel with four stacked cells and icons"},{"title":"1 用户交互层","position":"top horizontal layer","count":5,"labels":["桌面客户端 UI","会话面板 / Chat","项目工作区","任务与历史","设置与权限"],"container":"wide rounded white panel with blue border"},{"title":"2 Agent 编排层","position":"second horizontal layer","count":7,"labels":["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","权限与安全策略","Workflow Orchestrator / 工作流编排"],"container":"wide rounded white panel with faint purple-blue tint"},{"title":"3 能力执行层","position":"third horizontal layer","count":8,"labels":["文件系统 File System","代码编辑器桥接 IDE Bridge","Terminal / Shell","Git 与版本控制","搜索与检索 RAG","Browser / HTTP 工具","测试执行器 Test Runner","Patch / Diff 执行器"],"container":"wide rounded white panel with faint teal tint"},{"title":"4 模型与服务层","position":"fourth horizontal layer","count":5,"labels":["云端大模型 API","本地模型 Runtime","Embedding / Reranker","语音 / OCR（可选）","第三方 Agent 服务"],"container":"wide rounded white panel with blue border"},{"title":"5 数据与状态层","position":"fifth horizontal layer","count":6,"labels":["项目索引","Vector Store","本地缓存 Cache","会话状态 State","配置中心 Config","日志与审计 Logs"],"container":"wide rounded white panel with faint green tint"},{"title":"6 系统集成层","position":"bottom horizontal layer","count":6,"labels":["操作系统集成","权限沙箱 Sandbox","文件监听 Watcher","通知服务","后台守护进程 Daemon","自动更新 Updater"],"container":"wide rounded white panel with blue border"}],"centerpiece":"six stacked architecture layers in the middle with side governance columns","connectors":"dashed double-headed arrows connect each central layer to both sidebars; vertical blue arrows flow downward between central layers; small upward gray arrows rise from the bottom integration layer into the data layer","footer":{"count":1,"text":"特性： 本地优先 · 可插拔工具 · 人机协同 · 安全可控 · 支持离线/云端混合部署","position":"bottom center"}},"rendering":{"flat_vector":true,"high_resolution":true,"sharp_lines":true,"balanced_whitespace":true,"professional_pitch_deck_quality":true}}

Prompt structure
  • Modelgpt-image-2
  • Use casesocial-media-post
  • Styleminimal, editorial
  • Aspect ratioFlexible
Best used for
  • Use casesocial-media-post
  • Styleminimal, editorial
  • Recommended specs1:1, 4:5, 16:9, or 9:16
  • ModelGPT Image 2
How to customize

Use this 桌面端 AI Agent 架构图 prompt as a base. Replace the subject, product details, environment, lighting, brand colors, and output ratio while keeping the social-media-post intent and minimal, editorial direction stable.

Recommended specs

Choose the frame for the destination first, then use 1K, 2K, or 4K based on output quality needs. Product images and posters usually benefit from higher resolution.

Related prompts

Browse all prompts
Copy this GPT Image 2 prompt for brand identity and poster with Cinematic styling. Use it in Image2Studio to generate, edit, and save production-ready.
Poster

电影质感拳击比赛海报

A gritty, cinematic boxing promotional poster featuring a face-to-face staredown between {argument name="fighter 1" default="Mike Tyson"} on the left and {argument name="fighter 2" default="Sam Altman"} on the right. The left fighter is an older, bald man with a tribal facial tattoo, wearing a black boxing glove with "TYSON" printed on it. The right fighter is a younger man with dark wavy hair, wearing a black boxing glove featuring the OpenAI logo and text. Both men have intense, serious expressions, with highly detailed skin textures and sweat. The background is an out-of-focus boxing ring under bright stadium lights. The poster has a vintage, slightly scratched grunge texture. At the top, text reads "WORLD TECH vs BOXING CHAMPIONSHIP" in white and "{argument name="top tagline" default="NO CODE. ALL CHAOS."}" in red. In the center, large bold typography reads "MIKE TYSON" in red, "★ VS ★" in red, and "SAM ALTMAN" in large cream-white letters. Below this, text reads "{argument name="middle tagline" default="THE BRAWN. THE BRAIN. THE FUTURE."}". At the bottom, 3 columns of text display "{argument name="event date" default="SAT JULY 26"}", "LIVE ON PAY-PER-VIEW" in red, and "AT&T STADIUM ARLINGTON, TX". The very bottom footer reads "PRESENTED BY NETFLIX | TESLA | OPENAI".

Generate with this prompt
Copy this GPT Image 2 prompt for app ui mockup and ui mockups with Isometric, 3D Render, Editorial, Minimal styling. Use it in Image2Studio to generate,.
Poster

AI 编程助手宣传信息图

{ "type": "app promotional infographic poster", "style": "clean, modern, glassmorphism, soft shadows, 3D icons", "theme": "{argument name=\"primary color theme\" default=\"blue and white\"}", "header": { "title": "{argument name=\"app name\" default=\"CodePilot\"}", "subtitle": "{argument name=\"subtitle\" default=\"你的 AI 编程副驾驶\"}", "features_list": "智能补全 · 代码生成 · 问答调试 · 代码解析", "main_icon": "glossy 3D rounded square, blue gradient, white {argument name=\"main icon symbol\" default=\"</>\"} and sparkles" }, "layout": { "sections": [ { "title": "feature_cards", "position": "middle grid", "count": 4, "items": [ { "label": "智能代码补全", "icon": "blue lightning bolt", "description": "上下文感知, 精准补全 让编码更快一步", "ui_element": "macOS style code window with Python calculate_total function" }, { "label": "AI 代码生成", "icon": "purple magic wand", "description": "根据自然语言描述 一键生成函数 & 脚本", "ui_element": "chat prompt bubble and code window with Python quick_sort function" }, { "label": "对话 & 调试助手", "icon": "green chat bubble", "description": "自然语言提问、定位 Bug 边聊边改, 高效解决问题", "ui_element": "chat interface with user question and green AI resolution bubble" }, { "label": "代码解析 & 注释", "icon": "orange document with magnifying glass", "description": "快速理解复杂代码 自动生成注释与说明", "ui_element": "code window with JS fetchData function and 3 floating action tags: 自动注释, 逻辑解析, 一键复制" } ] }, { "title": "为什么选择 CodePilot?", "position": "bottom left", "count": 4, "labels": ["提升效率", "精准可靠", "隐私安全", "易于集成"], "icons": ["clock", "checkmark", "shield", "puzzle piece"] }, { "title": "立即体验", "position": "bottom right", "count": 1, "elements": ["GitHub 开源项目", "{argument name=\"github link\" default=\"github.com/op7418/CodePilot\"}", "QR code"] } ] } }

Generate with this prompt
Copy this GPT Image 2 prompt for avatar and infographics with Editorial styling. Use it in Image2Studio to generate, edit, and save production-ready images.
Portrait selfie

详细医学解剖信息图

{ "type": "medical infographic poster", "title": "{argument name=\"main title\" default=\"HUMAN ANATOMY - ANTERIOR VIEW\"}", "subject": { "description": "Full-body {argument name=\"subject type\" default=\"male human figure\"}, anterior view, split vertically down the midline.", "viewer_left_side": "{argument name=\"left side focus\" default=\"superficial muscles\"}", "viewer_right_side": "{argument name=\"right side focus\" default=\"bones, internal organs, arteries, veins, and nerves\"}", "style": "{argument name=\"color palette\" default=\"clinical medical textbook colors\"}" }, "layout": { "centerpiece": "The anatomical figure stands centrally, arms slightly away from the body, palms facing forward.", "labeling_system": "Thin black leader lines connect anatomical structures to text labels arranged neatly on the left and right margins.", "label_counts": { "head_and_neck": 12, "torso_and_arms": 29, "hands": 10, "pelvis_and_legs": 34, "feet": 5 }, "panels": [ { "title": "LEGEND", "position": "top-right", "count": 5, "items": [ {"color": "red/brown", "label": "MUSCLES"}, {"color": "beige", "label": "BONES"}, {"color": "yellow", "label": "NERVES"}, {"color": "red", "label": "ARTERIES"}, {"color": "blue", "label": "VEINS"} ] }, { "title": "NOTES", "position": "bottom-right", "count": 4, "items": [ "1. Right side shows bones, organs, arteries, veins and nerves.", "2. Left side shows superficial muscles and related tendons.", "3. Some deeper structures are illustrated transparently.", "4. Not all anatomical variations are shown." ] }, { "title": "SCALE", "position": "bottom-left", "count": 6, "description": "A horizontal bar scale with 6 numeric markers (0, 10, 20, 30, 40, 50) labeled 'Centimeters'." } ] } }

Generate with this prompt
Copy this GPT Image 2 prompt for food menu visual and logo branding with Photorealistic, Watercolor styling. Use it in Image2Studio to generate, edit, and.
Photography

快餐虾堡广告海报

A commercial food photography poster for a {argument name="burger type" default="shrimp burger"}. The central burger features a glossy brioche bun, lettuce, white sauce, spicy orange mayo, two grilled shrimp, and a thick crispy breaded patty. It rests on parchment paper on a wooden table, flanked by seasoned french fries on the left and two fried shrimp pieces on the bottom right. A blurred glass of iced cola and a faint {argument name="brand name" default="LOTTERIA"} logo appear in the dark background. The parchment bears a circular "SHRIMP BURGER" stamp. Top left Korean text reads {argument name="top left text" default="탱글한 통새우살이 입안 가득"}. The large central headline is {argument name="main headline" default="통새우 크런KIM버거"} with a small orange shrimp illustration. Below it is the subtitle {argument name="subtitle text" default="매콤바삭, 육즙가득! 올봄, 새우버거의 기준이 바뀐다!"}. The bottom left corner shows the {argument name="brand name" default="LOTTERIA"} logo. Warm, professional studio lighting.

Generate with this prompt
Copy this GPT Image 2 prompt for social media post and character design with Photorealistic styling. Use it in Image2Studio to generate, edit, and save.
Photography

日本突发新闻播报生成器

A photorealistic television news broadcast scene. On the right, a young Japanese female news anchor with shoulder-length dark brown hair and bangs looks directly at the camera with a professional expression. She wears a dark navy blazer over a white top, small earrings, and a lavalier microphone. The studio background features modern blue and silver illuminated panels. On the left, a large monitor displays a news graphic. The top of the monitor reads "{argument name="game name" default="Tokitori"}" followed by "{argument name="monitor top text" default="世界でも大人気のヒヨコゲーム"}". The left side of the monitor shows game cover art featuring a {argument name="character description" default="round, yellow chick character with big eyes"} on a green field, with the title "{argument name="game name" default="Tokitori"}" and text reading "{argument name="monitor achievement text" default="Steam売上 宇宙1位"}", "販売本数 1億本突破", and "同時接続数 345万人". The right side of the monitor displays a line graph titled "売り上げ推移" with an upward-trending yellow arrow, y-axis labels "0", "5000万", and "1億", and 3 x-axis dates "4/1", "4/10", and "4/20". A flat 2D version of the yellow chick sits on the graph line. Across the bottom of the screen is a prominent red lower-thirds breaking news banner. The left side of the banner has a box reading "速報" and the main text reads "{argument name="breaking news headline" default="TokitoriがSteam売り上げ宇宙1位に"}".

Generate with this prompt
Copy this GPT Image 2 prompt for social media post and infographics with Minimal, Editorial styling. Use it in Image2Studio to generate, edit, and save.
Poster

编辑级双轴数据信息图

{ "type": "editorial infographic dual-axis line chart", "style": "clean, newspaper-style, off-white background, highly legible typography", "header": { "category": "CRIME, SAFETY & JUSTICE (red text with red square icon)", "headline": "{argument name=\"main headline\" default=\"Crime is down 50% since 1993. Most Americans think it's going up. Both true simultaneously.\"}", "sub_headline": "US VIOLENT CRIME RATE vs PUBLIC PERCEPTION · 1990-PRESENT · BJS/FBI + GALLUP" }, "chart": { "x_axis": "Years 1990 to 2024 with 8 tick marks", "left_y_axis": { "color": "blue", "label": "{argument name=\"left axis label\" default=\"VIOLENT CRIME RATE per 100,000 people\"}", "range": "200 to 800" }, "right_y_axis": { "color": "red", "label": "{argument name=\"right axis label\" default=\"% OF AMERICANS WHO SAY 'CRIME IS UP FROM LAST YEAR'\"}", "range": "20% to 80%" }, "data_series": [ { "name": "Reality", "style": "solid blue line", "trend": "peaks early then drops significantly", "annotations": [ "1993 PEAK 747 violent crimes per 100,000 (with blue dot)", "REALITY: Crime Has Fallen (with blue arrow pointing to line)", "2024 376 per 100,000 ~50% LOWER than 1993 (with blue dot)" ] }, { "name": "Public Perception", "style": "dashed red line", "trend": "remains relatively flat and high", "annotations": [ "PUBLIC PERCEPTION: Remains High... (with red arrow pointing to line)", "2024 62% think crime is up (with red dot)" ] } ] }, "callout_box": { "position": "bottom left inside chart area", "style": "light yellow rectangle", "icon": "lightbulb", "text": "{argument name=\"callout text\" default=\"The crime rate and the public's feeling about crime have almost no relationship.\"}" }, "footer": { "text": "SOURCE: {argument name=\"footer source\" default=\"Bureau of Justice Statistics NCVS · FBI Uniform Crime Reports · Gallup Crime Poll\"}" } }

Generate with this prompt