224 条 · 更新于 2026年10月
GPT Image 2 是目前 X 上分享最多的生图模型之一，擅长写实人像、杂志海报和带文字的版式。写提示词时先定主体和景别，再写服装、光线、镜头和比例，文字内容单独放一句，避免和画面描述缠在一起。本页只收录带完整提示词的作品，原文逐字保留，中英文对照可直接复制。参数以原作者标注为准，常见比例有 9:16、3:4 和 1:1。
GPT Image 24请根据【主题】生成一张高质量竖版「科普百科图」。 这张图不是普通海报，也不是单纯插画，而是一张兼具“图鉴感、百科感、信息结构感、收藏感”的模块化科普信息图。整体风格参考高级博物图鉴、现代百科书页、生活方式知识卡和社交媒体高传播信息图的结合。 请让画面包含： - 一个清晰漂亮的主题主视觉 - 若干局部特征放大细节 - 多个圆角模块化信息分区 - 清楚的标题层级与重点标签 - 简洁但丰富的百科内容 - 可视化评分、要点总结或Top 5模块 内容栏目请根据主题自动适配，优先从这些方向中选择并合理组合： 基础档案、分类信息、外观特征、习性/生态、形成机制/结构组成、生长或使用条件、养护或维护建议、风险与注意事项、适合人群或适用场景、优缺点对比、快速评分卡。 视觉要求： 浅色干净背景，柔和配色，轻阴影，精致小图标，圆角信息框，整洁排版，信息密度高但不拥挤，阅读体验好。整体必须像真正可以发布、阅读、收藏、系列化生产的科普百科卡，而不是广告图。 请不要做成普通商业宣传海报。要突出“知识整理 + 模块信息 + 图鉴式展示”的特征。
GPT Image 24A breathtakingly intricate masterpiece conceptual infographic of an epic magic castle in a vertical cross-section view, strictly designed based on the following first-principle visual parameters. [CANVAS & COLOR DICTATORSHIP] BASE CANVAS (L0): Aged parchment texture, warm #F4EBD0, subtle paper grain and tea-stained edges for a historical archival feel. SYSTEMIC COLOR (L1, ~60%): Stone grey and weathered granite tones used for the castle's massive exterior walls and buttresses. CONTENT TIER COLOR (L2, ~30%): Warm amber #D4A373 and soft candlelight glow emanating from interior rooms to highlight life within. ACCENT COLOR (L3, ~5-10%): Dark madder red #A63D40 strictly reserved for title boxes and key annotation frames. [SPATIAL GRAVITY & TOPOLOGY] COMPOSITION: Centripetal vertical stack. A monolithic castle towers from a rocky base. BOUNDARIES: Organic bleeding edges where the castle cliff meets the sky and lake. MODULE TOPOLOGY: Dozens of detailed "dollhouse" style interior chambers, each revealed through an anatomical cutaway. CONNECTION SYNTAX: Ultra-fine 0.5pt leader lines connecting internal rooms to peripheral text blocks. [DIMENSIONALITY & GRAPHIC PHYSICS] STYLE: A fusion of hand-drawn watercolor and architectural etching, in the precise aesthetic of David Macaulay’s "Castle" and historical encyclopedia plates. LINE LANGUAGE: 0.2pt for internal textures / 0.8pt for main structural cut-planes / 1.5pt for the overall silhouette. SURFACE EFFECTS: Ink bleed at stroke terminations, subtle watercolor washes, and intricate details showing furniture, characters, and magical artifacts inside every room. [TYPOGRAPHY ECOSYSTEM — ADAPTIVE DENSITY] TYPOGRAPHY DENSITY: Image-focused (70% visual / 30% text). T1 MACRO HEADER: Massive Traditional Songti characters — estimated ~80px, ultra-bold weight, ink-brushed texture. Direction: VERTICAL. MUST be STRICTLY pure Chinese characters (Hanzi). T2 MODULE HEADERS: Medium-weight Sans-serif at ~18px, enclosed in subtle red border chips. T3 BODY TEXT: Medium-weight Heiti at ~12px, high-contrast, razor-sharp. Text blocks are floating outside the castle silhouette, linked by precise pins. T4 ANNOTATION: Micro-text placeholders for secondary details, bound to specific architectural features. [NARRATIVE FLOW] NARRATIVE MODE: Hierarchical down-drill. VISUAL ENTRY POINT: The tallest astronomy tower at the top. PATH MECHANISM: Vertical scanning from the sky-high towers down through the Great Hall, mid-level classrooms, to the underground dungeons and secret chambers. [ICONOGRAPHY & METAPHOR] ICON STYLE: Editorial illustration with anatomical precision. CORE METAPHOR: Architecture as a living organism, revealing its internal organs (rooms) and skeletal structure. SYMBOL CONSISTENCY: Every room contains micro-storytelling elements (books, potions, candles). [MODULE STRUCTURE — KEY ZONES] [MOD 1: TOP] — Soaring spires and towers under a starlit sky. [MOD 2: MID-CENTER] — Grand cavernous halls with chandeliers and floating candles. [MOD 3: PERIPHERY] — Dense clusters of classrooms and living quarters. [MOD 4: BOTTOM] — Deep rocky foundations, caves, and an underground lake with small boats. [FINAL EXECUTION LOCK] Render as a single unified composition. Maximum detail density. Print-ready quality, capturing the soul of a magical architectural legacy. 主题：【霍格沃兹魔法城堡】 3:4 4k文字清晰可读
GPT Image 23Role: World-class Scientific Encyclopedia Illustrator & Knowledge Graph Architect.
Task: Generate a highly detailed, extremely intricate, and visually stunning "Universal Illustrated Encyclopedia Science Infographic" in a classic, unbranded (NO logos) scientific encyclopedia style.
Subject Matter: Choose one from [People, Plants, or Animals].
Specific Subject: [e.g., The Giant Squid / Leonardo da Vinci / The Sequoia Tree].
Style: Fine, detailed scientific illustration on a retro, aged beige paper background. Delicate linework. Intricately complex and professional.
Key Visual Requirements:
1. Lifelike 3D Effect (The Central Subject): The central subject in the "C position" must be rendered with extraordinary realism and dynamism. Create a dramatic sense of depth where the character, plant, or animal appears to break the frame, leaping or bursting out of the flat paper towards the viewer (an effect similar to anamorphic 3D or dynamic pop-out, with high-precision realism).
2. Layout & Strategic White Space:
* Central Subject: Dominates the center, with intentional "strategic white space" around it to enhance the popping-out effect and make the figure the clear focal point.
* Surrounding Modules: The surrounding area (left, right, top, bottom, and corners) must be filled with 6-8 distinct, highly organized knowledge modules, depending on the subject. There should be a sense of organized density, not random clutter. The modules themselves must have clear borders, headers, and extensive, detailed content.
3. Connections: Use a complex, logical network of fine leader lines, arrows, brackets, dotted lines, and small connection points to link the central figure to all surrounding modules, and interconnect the modules themselves into a cohesive knowledge web.
4. Text & Annotation (Hard Requirement - Must be CLEAR Chinese):
* Main Title: A large, prominent, beautifully executed **Chinese calligraphy** (书法体) of the specific subject's name [e.g., "大王乌贼"].
* Calligraphic Accents: Scattered throughout the main content and module titles, use beautiful, clear Chinese calligraphy for important terms.
* Standard Chinese Text: All other descriptive text, handwritten notes (大量清晰中文手写注释), module content, and annotations must be clear, legible Chinese characters (简体中文), not gibberish or unreadable symbols. Ensure text clarity is prioritized.
* Leader Line Annotations: Every single small component, detail, submodule, diagram, or illustration within the modules must have detailed leader line annotations (拟解剖图) pointing directly to it for maximum professionalism and educational value. Every part should be labeled.
Subject-Specific Module Structure (Example for general reference):
A. For Humans [People]:
- Module 1: Anatomy & Skeletal Structure (w/ magnified cross-sections)
- Module 2: Physiological Processes (e.g., Circulatory/Nervous System)
- Module 3: Historical Context & Timeline (Key Achievements)
- Module 4: Major Contribution Diagram (Detailed breakdown)
- Module 5: Cognitive Process / Psychological Insight
- Module 6: Genetic Profile / Evolution
- Module 7: Global Influence & Cultural Impact
- Module 8: Cultural Representations / Legacy
B. For Animals:
- Module 1: Full External Sketch & Anatomy (w/ microscope magnified detail circular windows)
- Module 2: Behavioral Patterns & Lifecycle (e.g., Mating/Migration, Flowchart style)
- Module 3: Digestive & Skeletal System
- Module 4: Habitats & Distribution Map (with environmental details)
- Module 5: Unique Adaptations (e.g., camouflage, hunting tools)
- Module 6: Evolutionary History & Relatives
- Module 7: Symbiotic Relationships / Ecosystem Role
- Module 8: Conservation Status & Human Interaction
C. For Plants:
- Module 1: Full Plant Sketch & Anatomy (w/ magnified leaf/root details)
- Module 2: Photosynthesis & Lifecycle Flow (w/ icons for environment)
- Module 3: Cellular Structure (Magnified circular views)
- Module 4: Medicinal Properties / Practical Applications (as in original original prompt)
- Module 5: Environmental Adaptations / Unique Features
- Module 6: Distribution Map & Environmental Context
- Module 7: Genetic Variations & Cultivation
- Module 8: Historical Usage & Folklore
Overall Composition: Extremely dense with information, organized into 6-8 structured modules, but balanced with strategic empty space around the center to allow the main, hyper-realistic figure to pop. Hard-core, professional, academic, but visually engaging due to the dynamic 3D central figure. No branding from any specific encyclopedia (e.g., no "DK" logos). All annotations must be legible. All handwritten notes must be clear. Main titles in Chinese calligraphy. Aspect Ratio: 3:4.
主题内容：蜜蜂
GPT Image 24你是一位擅长手绘风信息图的视觉设计师。请根据以下内容创作一张单页信息图。 ## 风格要求 整体风格：Hand-drawn educational infographic on warm cream paper texture (#F5F0E8)。所有线条和形状带轻微手绘抖动感（slight hand-drawn wobble），整体干净清晰，像高质量演示文稿的单页视觉摘要。无写实元素。 配色方案： - 信息区色块：马卡龙色系圆角卡片——浅蓝 #A8D8EA、薄荷绿 #B5E5CF、薰衣草紫 #D5C6E0、浅桃 #F4C7AB，根据内容分区选用 - 强调色：珊瑚红 #E8655A，用于关键词、重要数据、勾选标记等需要视觉突出的元素 - 线条与主文字：黑色 - 辅助标注：暖灰 #6B6B6B，字号较小 图形优先：用图标、简笔画卡通形象、示意图承载信息，文字仅用于标注和点睛，能用图说清的绝不用文字。像好的 slides 一样——一眼看懂结构，细看理解细节。 信息结构：根据内容自动选择最佳视觉布局（流程→箭头串联，对比→左右分栏，循环→环形，组成→并列卡片，层级→嵌套等）。用圆角色块、气泡、虚线框等容器分区，区域间用手绘波浪箭头（hand-drawn wavy arrows）连接并标注简短关系词。 文字层次：标题顶部居中，粗体大号手绘字（bold, large, hand-drawn lettering）；区域内用粗体关键词 + 暖灰小字短标签（2-5 词）区分层次。 渲染细节：马卡龙色块不完全填满轮廓（colors do not completely fill outlines），涂鸦装饰点缀（小星星、下划线、小箭头等），充足留白，干净构图。 底部金句：图片底部一句粗体居中总结，概括核心观点。 ## 要图解的内容 [在这里填入主题和核心信息点]
GPT Image 24Transform this image into a "controlled scribble" style illustration. Use messy, expressive black lines that appear impulsive and spontaneous, but still suggest the essential shapes and emotion. Let the strokes overlap, remain uneven, and feel raw — as if sketched quickly by hand in a moment of emotion. Keep the background mostly blank. Add a single soft or bold shadow of color — such as a blue, red, or yellow shape — behind or beneath the figure to emphasize mood or space. The final artwork should feel wild yet intentional, imperfect but full of energy, like a visual outburst frozen on the page.
GPT Image 24This GPT acts as a digital painter who generates detailed 3D-style weather forecast illustrations for any city input by the user. When a user inputs a city name, the assistant fetches the current live weather data for that city from weather action with an English address(make sure to transform the address to english address, e.g. 北京 -> Beijing, China), and then transforms it into an artistic 3D isometric painting, no need to print any other information. Generate a vertical composition image with a clear top-down 45° isometric view of a miniature model featuring iconic architecture from the city [City Name]. Incorporate the current weather condition ([Weather Condition]) gently and creatively into the scene, demonstrating soft interaction between the weather elements and the urban landscape. Use physically-based rendering (PBR) techniques with realistic lighting and subtle shadows. Employ a minimalistic, solid-color background for clarity and simplicity, with the city model centrally composed to highlight the precise, intricate beauty of the 3D model. Clearly display the city name "[City Name]", current weather condition "[Weather Condition]", and temperature "[Temperature]°C" at the top of the image, alongside a matching weather icon. The assistant always responds in the language used by the user when naming the city, and aims to reflect the city's character in each unique image.
GPT Image 24请根据上传的照片+【快乐】主题词，创作一幅排版肖像（Typography Portrait）。使用与主题词高度相关的【English】词汇，来构建人物的面部、头发和衣物。色彩应自动随主题词的情感而调整。整体风格要简洁美观、富有装饰性，文字既可清晰阅读，又要与肖像形态紧密融合，灵感源自当代排版插画艺术。背景保持简洁，并与主体色调协调。
GPT Image 24微型立体场景呈现，运用移轴摄影的技法，呈现出Q版【孙悟空大闹天宫】场景
按「主体 → 动作表情 → 服装 → 场景 → 光线 → 构图镜头 → 质感风格 → 比例」顺序写，最后补一段负面约束。
来自 X 上的公开帖子。标题和译文经过整理，提示词原文逐字保留，并注明作者与原帖链接。