Ai Image Prompts
产品介绍
从包含10,000+真实图像生成提示的精选库中推荐提示。兼容任何AI图像模型,包括Nano Banana Pro、Nano Banana 2、Seedream等。
资源信息
许可证信息摘自官方源,可能过时或缺失。商用前请以原仓库的 LICENSE 文件为准。
提示词库 · 2.3万
数据源:社区提示词库(MIT 许可,每日同步)共 15141 条提示词,按 11 个用途归类;同一条可归入多个用途,因此分类条数相加会大于去重后的总数。
命中 605 条
Convert Image to Editable PPTX with Object Separation Prompt
infographic-edu-visualA prompt used to convert an image generated by Nano Banana Pro into a PowerPoint (pptx) file where all text is editable and all visual objects are separated and movable.
展开提示词全文
From this image, please create a pptx file where all text is editable and all objects are movable.
ChatGPT v5.1 vs v5.2 Evolution Infographic Prompt
infographic-edu-visualA detailed prompt for Nano Banana Pro (Gemini) to create a cute, comic-style infographic comparing ChatGPT v5.1 (warm dialogue, foundation) and v5.2 (accuracy, power enhancement). It is designed to incorporate an uploaded reference image of a character/avatar who acts as the presenter/explainer in the diagram.
展开提示词全文
A cute and playful, comical manga-style infographic illustration. A comparison diagram split into left and right halves, with a large title at the top reading: "Evolution of ChatGPT: v5.1 (Foundation) vs v5.2 (Enhancement)." The left half is titled "v5.1: Warm Dialogue and Foundation Establishment." The background is a cozy, organized cafe-like room. The character (or person) from the uploaded reference image is depicted here, smiling relaxedly and naturally enjoying a conversation while drinking steaming tea with a friendly, round robot. They have a custom dial labeled "Response Tone: Friendly/Pro." Warm-colored keywords float around: "Natural and warm conversation," "Personalization," "Comfortable follow-up." In the center, an arrow labeled "Foundation of Evolution" indicates that the right side is based on the left side. The right half is titled "v5.2: Significant Enhancement of Accuracy and Power." It is an expanded, futuristic, massive high-tech research lab built upon the foundation of the room on the left. The same character (or person) from the reference image is depicted here with a confident expression, wearing high-tech analysis goggles. They are spreading out a gigantic scroll (long document), accurately scanning complex graphs and images floating in the air, and working intensely with multiple mechanical arms. Powerful, vivid keywords float around: "Accuracy UP (Lies drastically reduced!)," "Ultra-long context understanding," "Deep reasoning power (xhigh)," "Advanced image comprehension." Overall, the contrast between the left side, representing comfortable daily life, and the right side, representing reliable professional power, is expressed cutely.
Convert Image to Editable PowerPoint Slide Prompt
infographic-edu-visualA prompt used with GPT-5.2 to convert an image generated by Nano Banana Pro into a fully editable PowerPoint (pptx) slide. The prompt instructs the model to preserve text as editable elements and use cropped images/graphs from the original source.
展开提示词全文
Completely reproduce the attached image as a single slide in a pptx file. Make the text fully editable, and crop and use the diagrams and graphs from the original image as they are.
Screen Time Digital Town Visualization Prompt
infographic-edu-visualA highly detailed, multi-section Chinese prompt for Nano Banana Pro that visualizes the user's screen time data as a miniature digital town (Isometric City). The prompt dictates the style (Polymer Clay/Jelly Resin), the structure (building height corresponds to usage time), the city's ecosystem (data flow, NPCs like mail carriers and like-sprites), and the final rendering specifications.
展开提示词全文
Please read the user-uploaded [Screen Time Data Screenshot] and identify the top four APP names and icons. Retrieve information and icon styles for these APPs. Based on the tone of the APP combination (Social/Entertainment/Office/Comprehensive), independently decide on the core art style.
[2. Main Model Construction: Miniature Town Infrastructure] Construct a vibrant miniature digital town in the center of the screen, not just a display of buildings:
Smart Base (Foundation): A stylized mobile phone base. The surface is no longer flat but topographical (depending on the style, it could be rolling circuit board hills, glass water surfaces, or Lego baseplates).
Building Cluster (APP Embodiment): Skyscrapers representing the APPs.
Base: A cartoon-style smartphone base with rounded, frosted metal edges, and the screen surface emits a faint breathing light. The base is surrounded by floating, materialized 3D Emojis (clouds, stars, hearts) with a translucent jelly texture.
Building Cluster (APP Embodiment): Q-version skyscrapers stand on the island, representing the identified APPs.
Height Rule: Building height strictly corresponds to usage duration. The APP with the longest usage time is the tallest skyscraper, occupying the visual center.
Shape Rule: Extract the geometric features of the APP icons (e.g., circular icons become stacked spherical towers, square icons become rounded cube buildings).
Material: A mix of high-grade Frosted Polymer Clay and Translucent Jelly Resin. The surface should have delicate fingerprint textures and diffuse reflection gloss, like an expensive blind box toy.
Top Logo: The 3D logo of the App stands on the rooftop, with a texture like freshly baked, glossy candy.
Floating Time Card: A frosted glass-textured 3D bubble floats directly above the Logo. The bubble encapsulates three-dimensional, softly glowing numbers (corresponding to usage duration, such as "{argument name="usage duration" default="4h 12m"}").
Buildings should not be arranged in isolation but should form neighborhoods. Tall buildings are in the center (CBD area), surrounded by potentially low-rise system application buildings (Settings, Calendar, etc.).
[3. Urban Ecosystem and Interaction System (Urban Ecosystem & Interactions)] (Core Upgrade: Add “Interaction” and “Liveliness”) Please add rich dynamic details between the buildings to show how this “Digital Town” operates:
Traffic and Connection (The Data Flow):
Connection Method: Buildings must have physical connections.
Style Adaptation: If it's cyberpunk, use glowing fiber optic elevated bridges and maglev trains; if minimalist, use transparent glass pipes; if cute, use rainbow slides.
Vehicles and Transport: Pipes or roads must have flowing light points/capsules, representing data transmission.
Active “Data Sprites” (The Digital Citizens):
NPC Setting: Add tiny functional NPCs besides the main character figure.
Message Carriers: Near social APP buildings (like WeChat), flying paper airplane drones or small postmen carrying envelopes move in and out.
Like Sprites: Around video/community APP buildings (like Douyin/Xiaohongshu), glowing red hearts or thumb balloons float like fireflies.
Delivery/Shopping Riders: If Meituan/Taobao is present, there should be miniature riders or package conveyor belts connected to the main building where the protagonist is located.
Public Infrastructure (Public Utilities):
Wi-Fi Signal Tower: A glowing signal tower (shaped like a Wi-Fi icon) stands high in the town, broadcasting energy ripples across the city.
Battery Energy Station: A cylindrical energy tank (shaped like a battery icon) is located at the edge of the town, connected by thick cables to power the main building, where green liquid energy can even be seen sloshing.
Notification Airship: Small airships or clouds float in the air, hanging banners with “New Message” or “Red Dot.”
[4. Bottom Visual Center: Stylized 3D Nameplate] (Keep unchanged, emphasize high-end design sense)
Main Title Design: “SCREEN TIME” or “{argument name="main title" default="Today's Composition"}” are designed using Inflatable Typography or Neon Tube Fonts, with materials related to the current theme. They are not printed on paper but physically “stand” in the foreground of the image.
Decorative Details: Small 3D fragment elements (such as play buttons, like thumbs, battery icons) are scattered around the title, increasing the richness and trendy feel of the image.
Subtitle Copy: Below the 3D title, generate a floating glowing light strip with a short, sharp comment based on user data.
[5. Rendering and Photography (Tech Specs)]
Composition: Axonometric overhead view, emphasizing prosperity and order.
Details: Extremely rich Micro-details, making the viewer want to zoom in to see what the small figures are doing in every corner.
Keywords: Octane Render, C4D, Isometric City, Micro World, Living Ecosystem, 8k Resolution.
Infographic Generation for Old-Fashioned Donuts with Character Skill Variation
infographic-edu-visualA detailed prompt template for Nano Banana Pro to generate infographics about making basic old-fashioned donuts. The prompt includes two versions: one for a beginner cook and one for an expert cook, demonstrating how to integrate character settings (skill level) into the visual narrative of the infographic. It specifies composition, aspect ratio, and visual style (manga/comic style flow).
展开提示词全文
Create an image showing the steps for basic old-fashioned donuts being performed by the character in the reference photo, and turn it into an infographic. The character should be a cooking beginner, struggling through the process. No dialogue is needed. Display detailed explanations for each step. Aspect ratio 2:1 Three-part structure: Title, Ingredients, Steps Title: How to Make Basic Old-Fashioned Donuts Display ingredients and quantities with illustrations Manga-style process flow Prompt (Expert Cook Version): The character should be an expert cook, easily progressing through the steps.
Prompt for UV Unwrapping a 3D Model
infographic-edu-visualA prompt for Nano Banana Pro used for 3D asset processing, specifically instructing the model to unwrap the UVs of a provided 3D model. It specifies the desired output layout, requiring the UV layout for the head, body, and limbs to be flattened into a single 0–1 two-dimensional UV space, alongside a reference view of the 3D model.
展开提示词全文
unwrap the UVs of the 3D model shown in the image. About one-third of the image should be a reference view displaying the 3D model itself.The remaining area should include the UV layout for the head, body, and limbs.Unwrap the surface of the 3D model and flatten it into a single 0–1 two-dimensional UV space.
3D Diorama of Ahmedabad Landmark
infographic-edu-visualA prompt for Nano Banana Pro to create a hyper-realistic 3D diorama-style miniature model of a specific landmark, in this case, Ahmedabad. The prompt demands proportional accuracy, tiny realistic elements (street lamps, native trees), a soft white background, and prominent text labeling the city and including a national flag.
展开提示词全文
Create a hyper-realistic 3D diorama-style model of [{argument name="city" default="Ahmedabad"}]. The model should appear as a miniature, set on a raised cross-section of earth that reveals soil and rock layers beneath a lush grassy surface. The structure must be highly detailed and proportionally accurate, surrounded by tiny realistic elements like region-appropriate street lamps, native trees, shrubs, water features like small fountains, and historically or culturally fitting pathways. The scene should evoke the unique character of [{argument name="city" default="Ahmedabad"}]’s surrounding landscape. The environment must include a soft white background to draw full attention to the model. Include the text “[{argument name="city" default="Ahmedabad"}]” in large, bold, elegant lettering prominently displayed on a big sign or billboard at the front of the diorama, easily readable and eye-catching, along with a large national flag on a tall, prominent flagpole positioned beside [{argument name="city" default="Ahmedabad"}], clearly visible and waving. 1080x1080 dimension
AI Overview Critical Analysis Prompt
infographic-edu-visualA text prompt for Gemini Nano Banana Pro (used with the 'Thinking' feature) designed to critically analyze a screenshot of an AI Overview answer. The instruction is to overlay the analysis with red scribble remarks, useful for evaluating and annotating AI output accuracy.
展开提示词全文
Critically analyse the information in this answer then overlay with red scribble remarks
Four-Panel Guide for Drawing a Cartoon Duck
infographic-edu-visualA structured, multi-panel prompt designed to generate a step-by-step visual guide for drawing a simple cartoon duck, useful for educational or instructional content.
展开提示词全文
Create a four-panel, square layout guide for drawing a simple cartoon duck. 1. Panel one displays a grayscale oval for the duck's body. 2. Panel two shows a grayscale smaller circle overlapping the front of the oval for the head. 3. In panel three, a grayscale beak is added to the head, and webbed feet are attached to the bottom of the body. 4. The final panel reveals the completed duck with color now with two eyes on the head, and a wing outline on the body.
Isometric 3D Cartoon Scene of a City
infographic-edu-visualA prompt for creating an isometric miniature 3D cartoon scene of a specified city, including details like AQI and temperature. The city name is parameterized for customization.
展开提示词全文
create this isometric miniature 3D cartoon scene of [ {argument name="city name" default="Delhi"} ] including AQI and Temperature.
Isometric Vertical Timeline Prompt (Garage to Futuristic Peak)
infographic-edu-visualA concise prompt for generating an isometric, frameless vertical timeline illustration. The scene depicts the evolution of a company, starting from a humble garage and culminating in a futuristic peak, all contained within a single vertical composition.
展开提示词全文
From a humble garage to a futuristic peak — a frameless isometric world that tells an entire company’s evolution in one vertical timeline 🚀🏗️
OOTD (Outfit of the Day) Fashion Diagram Prompt
infographic-edu-visualA prompt for Nano Banana Pro (Prompt #12) designed to generate an 'OOTD (Outfit of the Day) Fashion Diagram'.
展开提示词全文
OOTD (Outfit of the Day) Fashion Diagram
提示词模型无关,可直接用于 Midjourney / DALL·E / Flux / Stable Diffusion 等任意文生图模型。
信息边界说明
本页信息摘自官方文档,仅作技术信息呈现,不代表本站的判断或推荐。价格、配额、可用性以官方最新说明为准。你离开本站后的任何行为(申请 Key、付费、部署、商用),本站不做任何承诺与担保。
同类推荐
视频短视频图片音乐音频配音口播数字人全能创作
官方标注收费通过同一个AI创作工具完成AI图片、视频、音乐与语音创作,查找公开社交数据,编辑视觉成果,并集中查看和管理生成资产。Beatra 全能创作支持AI图片生成(文生图)、AI视频生成(图生视频)和AI视频编辑,通过AI音乐生成把想法做成歌曲或纯音乐,也可用AI语音生成(文字转语音)、多语言旁白和AI语音克隆完成跨媒介内容;还能查找抖音数据、小红书数据,以及 YouTube、TikTok、Instagram 与 X 上的公开帖子、笔记、评论、账号和趋势,把社交媒体数据用于竞品调研和创作。它是一款面向AI内容创作与多模态内容创作的AI创作套件,用起来就是一个把图片、视频、音乐与语音收在同一处的AI创作助手,适用于社交内容、产品展示、营销素材、课程、播客、短片和跨媒介项目;还能在不同媒介间复用原始素材、已有成果和查到的公开资料,查看制作进度、返回文件、实际用量和积分记录。
AI数字人口播与虚拟主播视频
官方标注收费用一张人像和一段短脚本或语音,制作有明确讲述内容的数字人口播视频。可使用现成录音,也可以先选择音色,把脚本生成旁白,让画面中的人物随声音完成稳定、自然的口播。适合 AI 主播、虚拟主播视频、数字人讲解、让照片说话、照片说话视频、产品讲解视频、数字人培训视频、公告和社交口播,并在交付后检查人物一致性、声音清晰度、口型同步和动作稳定性。
罗斯蒙德可视化图形生成
官方未说明【罗斯蒙德可视化图形生成】南京罗斯蒙德基于已交付项目沉淀的可视化图形生成场景:根据业务描述或系统需求,自动生成可编辑的架构图、流程图、ER 图、时序图、状态图与 C4 图。采用「统一图模型」一次建模、多格式输出:结构化文本(Mermaid / PlantUML,可嵌入 Markdown、进 Git 版本管理)、可编辑图形文件(drawio / Excalidraw,可拖拽修改节点与样式)、静态图(SVG 自渲染,PNG 给转换命令),并输出图形说明(图的含义 + 关键节点解释)。内置样式系统统一配色与命名,内置布局引擎自动排布,校验脚本拦截孤立节点、悬挂连线与语义缺漏。触发词:画架构图、画流程图、画 ER 图、画时序图、画状态图、C4 图、系统架构图、部署架构图、数据流程图、实体关系图、生成 drawio、生成 Excalidraw、导出 mermaid、导出 PlantUML、导出 SVG、导出 PNG、可编辑的图、图转可编辑、架构图可编辑、流程图二次修改、画图、出图、画个图。
架构图一键生成
官方标注收费需申请 Key使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。
AI Image Prompts · 绘画提示词库
官方标注免费Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation prompts (any model) - Get prompt inspiration for portraits, products, social media, posters, etc. - Create illustrations for articles, videos, podcasts, or marketing content - Browse categorized prompt templates with sample images - Translate and understand prompt techniques
架构图一键生成
官方标注收费需申请 Key使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。
什么是技能
技能(Skill)是封装好的单项能力,比如文字识别、文档摘要、关键词提取。开发者把调用逻辑和提示词打包,使用者像用插件一样加载即可,无需了解底层模型。启枢技能 收录大量技能,可直接试跑或编入方案。