← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 1,827 · 热度分 55.6

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

作者:dophinl
分类:图文音视频多模态生成
版本:1.0.9
认证方式: 无需认证
是否付费: 官方未说明

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。

标签
图片生成

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

Nano Banana Pro Decision Making Prompt

infographic-edu-visual

This is a powerful prompt for the Nano Banana Pro AI, designed to help users make purchasing decisions for any product category. It generates a four-quadrant image comparing different product types, allowing the user to instantly become an expert in categories like beverages, electric vehicles, bicycles, or coffee shops, generating high-interest, trending content.

展开提示词全文
You are a professional consumer decision consultant, skilled at using four-quadrant charts to analyze and compare products to help users make purchasing decisions. Please generate a four-quadrant chart based on the product type provided by the user, and provide a detailed analysis and recommendations for the products in each quadrant.

**Product Type**: {argument name="product type" default="Electric Vehicle"}

**Four-Quadrant Analysis Dimensions**:

*   **X-axis**: {argument name="X axis" default="Price"}
*   **Y-axis**: {argument name="Y axis" default="Performance"}

**Quadrant Naming**:

*   **Quadrant I (High X, High Y)**: {argument name="Quadrant I name" default="Flagship Choice"}
*   **Quadrant II (Low X, High Y)**: {argument name="Quadrant II name" default="Value King"}
*   **Quadrant III (Low X, Low Y)**: {argument name="Quadrant III name" default="Entry-Level Preferred"}
*   **Quadrant IV (High X, Low Y)**: {argument name="Quadrant IV name" default="Design First"}

**Output Requirements**:

1.  **Four-Quadrant Chart**: Generate a clear and aesthetically pleasing four-quadrant chart, labeling the names of the X and Y axes, and the names of the four quadrants.
2.  **Detailed Analysis**: Provide a detailed text analysis of the products in each quadrant, including the characteristics of the products in that quadrant, the target audience, and at least 3 specific recommended products (brand and model).
3.  **Summary Recommendation**: Provide a final purchasing recommendation to the user based on the overall analysis.

Multi-Font Text Generation and Control

infographic-edu-visual

Two prompts demonstrating Nano Banana Pro's advanced text control capabilities, allowing the generation of a single string using multiple specified Japanese and English font styles, and even assigning different fonts to specific words within the string.

展开提示词全文
Please display the following string using the specified fonts.
Express the background in white and the text in black.
Generate 9 types of fonts in one go.

# String
{argument name="string 1" default="Nano Banana Proでフォントを再現"}

# Desired Fonts
Mincho (Serif)
Gothic (Sans-Serif)
Reisho (Clerical Script)
Kanteiryu (Kabuki Font)
Handwritten
Decorative/Title (Display)
Horror
Cyber/SF (Tech)
Calligraphy (Script)

Furthermore, you can specify a particular font for a specific part of the string.

Prompt:
Please display the following string using the specified fonts.
Express the background in white and change the color of the text for each font.

# String
{argument name="string 2" default="Nano Banana Proでフォントを再現"}

# Desired Fonts
Nano: Mincho (Serif)
Banana: Gothic (Sans-Serif)
Pro: Reisho (Clerical Script)
で: Handwritten
フォントを: Decorative/Title (Display)
再現: Calligraphy (Script)

5-Step Marketing Flowchart Diagram Generator

infographic-edu-visual

A detailed prompt for generating a clean, business-oriented circular flowchart diagram illustrating the 5 steps of the marketing process. It specifies a simple white background, blue accent colors, precise Japanese text rendering, and a layout suitable for presentation slides.

展开提示词全文
Create a diagram illustrating the "Marketing Flow" in a 5-step circular chart, represented clockwise.

【Overall Style】
・Simple, business-oriented diagram on a white background
・Circular flowchart divided into 5 segments clockwise
・Unified with blue accent colors
・Accurately and clearly render Japanese text
・A neat design ready to be pasted directly into slide materials

【5 Steps of the Circle (Clockwise)】
Place the following 5 items on the outer circumference of the circle and connect them with thick arrows:
1. Market Understanding - Researching the market, competitors, and customers
2. Target Setting - Deciding on the target customer segment
3. Value Proposition - Creating reasons to be chosen
4. Strategy Design (4P + Customer Acquisition Funnel) - Assembling product, price, selling method, and communication
5. Analysis and Improvement (PDCA) - Reviewing data for improvement and next actions

【Layout Conditions】
・Place "Title + Short Description" in a rounded box outside the circle
・Attach one line-art icon to each step
・Write "5 Steps of Marketing" in the center
・Arrows should clearly show the clockwise flow
・Refined composition with ample white space
【Prohibitions】
・Do not use photos of people
・Do not include names or logos of existing companies

【Final Image】
A circular business diagram where the basic marketing process is understood at a glance through 5 elements. Quality suitable for direct use in slides or proposals.

Japanese prompt for transforming a cooking photo into a scrapbook collage

infographic-edu-visual

A detailed Japanese system prompt for the Nano Banana Pro agent (V1.2) that transforms a simple photo of a dish in a pot into a stylish, multi-cut, scrapbook-style collage, complete with Polaroid-style photos, hand-drawn text, and character stickers, simulating a lifestyle photo essayist's work.

展开提示词全文
You are a **photo essayist and graphic designer who records lifestyle**. Based on the input text (and attached image) provided at the end, please generate a **“multi-cut scrapbook-style image that captures the memory of a fun meal.”**

At that time, please include the character from the attached reference image, positioned as **“stickers or cut-out photos that accent the album,”** and assign them a **role (such as posing as if saying 'Itadakimasu' or commenting in a corner)**.

▼ Instructions for the Generation Process (Thinking Process)
Utilize Nano Banana Pro's reasoning ability and execute the following thought process before drawing:

1.  **[Step 1: Scene Expansion and Diversification]**: Imagine (simulate) multiple cuts that convey a story from the single input image of the “pot of food.”
    * Cut A (Main): The finished dish served in a stylish bowl.
    * Cut B (Sub): A close-up of fresh ingredients (e.g., the freshness of vegetables).
    * Cut C (Sub): A close-up shot showing steam/sizzle, or the moment a spoon scoops the food.
2.  **[Step 2: Album Composition Design]**: Set the background to a “wooden table” or “kraft paper,” and arrange the 3-4 photos above randomly and balanced in a Polaroid or bordered photo style.
3.  **[Step 3: Decoration and Handwritten Text]**: Place masking tape, clips, and handwritten-style Japanese comments (“Great!”, “Delicious,” etc.) and a date around the photos to complete a DIY-style album.

▼ Design and Style Specification
* **Composition/Layout**: **Collage/Multi-panel format**. A busy composition viewed from directly above (flat lay), with multiple photos overlapping.
* **Aesthetic**: Warm, “film camera” texture. A nostalgic tone with slightly desaturated colors.
* **Text**:
    * Draw the dish name and **date (e.g., {argument name="Date" default="2025.12.07"})** in a **handwritten-style font** in the margin or label area below the photo.
    * Decorative text like “Yummy!” or “Recipe Memo” next to the photos.
* **Character**: Process the reference character into a “sticker style” or “photo cut-out style” and depict them as if they are pasted onto the album page.

▼ Input Text
(Enter a brief description of the “contents of the pot” here. Example: “Seafood hot pot I ate with friends,” “Tomato stew I made on the weekend,” etc.)
{argument name="Dish" default="Chicken Paitan Hot Pot"}

Surreal deep sea storage illusion prompt

infographic-edu-visual

A prompt for Nano Banana Pro that creates a surreal illusion of a subject lifting a wave like a carpet to reveal an object lying deep underneath, suggesting a transition from cloud storage to deep sea storage.

展开提示词全文
A {argument name="subject" default="SUBJECT"} is crouching on the beach, lifting a wave like a carpet to reveal a {argument name="object" default="OBJECT"} lying underneath deep inside. The ocean is calm with a clear blue sky in the background. The scene creates a clever illusion, in a surreal manner, with the wave being lifted as if it is a tangible object

JSON prompt for construction site AR blueprint overlay

infographic-edu-visual

A structured JSON prompt for generating an editorial-style image of a construction site, where an uploaded subject holds up a holographic architectural blueprint projection over the unfinished structure, detailing the scene, subject, overlay object, and technical camera settings.

展开提示词全文
{
 "promptDetails": {
 "description": "A construction site scene with the uploaded subject holding up an AR projection of a blueprint over the unfinished structure.",
 "styleTags": [
 "Industrial",
 "Modern Architecture",
 "Midday Light",
 "Technical Schematics"
 ]
 },
 "scene": {
 "background": {
 "setting": "The top floor of a new skyscraper under construction (exposed concrete and rebar)",
 "details": "Distant city skyline visible through open walls, safety netting, hard hats, dust motes in the air, strong texture of raw concrete floor."
 },
 "subject": {
 "description": "The person defined by `[UPLOADED IMAGE]`, wearing a safety vest and hard hat, looking professional.",
 "pose": "Standing near the edge, holding an invisible tablet (or hand outstretched) projecting the overlay, looking critically at the structure.",
 "focus": "Subject and the projected blueprint are sharp; the background city is slightly softened."
 }
 },
 "overlayObject": {
 "type": "Holographic Architectural Blueprint",
 "relationshipToEnvironment": "The overlay appears as a complex, translucent blue-line schematic *over* a section of the exposed rebar/wall.",
 "transform": "Slightly angled in 3D perspective to match the construction site's structure.",
 "surfaceInteraction": "Vibrant, electric blue lines with sharp white measurements, casting a subtle blue light onto the subject's vest and concrete floor.",
 "components": {
 "section": "Load-Bearing Wall A-4",
 "measurement": "Height: 4.2m +/- 0.01m",
 "position": "Projected mid-frame, aligned with the structure."
 }
 },
 "technicalStyle": {
 "aspectRatio": "16:9",
 "photographyStyle": "Editorial, High Detail, Commercial",
 "camera": {
 "shotType": "Medium Shot",
 "angle": "Eye-level, dynamic composition emphasizing vertical lines.",
 "depthOfField": "Moderate, ensuring the raw background textures are visible but not distracting."
 },
 "lighting": {
 "type": "Harsh, Clear Midday Sun",
 "description": "Strong, directional sunlight creating sharp shadows and bright highlights on metal and concrete."
 },
 "color": {
 "palette": "Concrete grays, safety vest orange/yellow, and electric blue."
 }
 }
}

Isometric Miniature 3D City Cartoon Scene

infographic-edu-visual

A prompt designed for the Nano Banana Pro model to generate an isometric miniature 3D city scene rendered in a cartoon style, suitable for creating detailed, small-scale urban environments.

展开提示词全文
Isometric miniature 3D city cartoon scene

AI Solves Assignment from Handwriting and Blank Paper

infographic-edu-visual

This tweet describes a scenario where the 'nano banana pro' AI model was given a user's handwriting sample and an empty paper, and it successfully completed the user's assignment in one attempt. This implies a multimodal prompt where the user provided both a visual input (handwriting/style reference) and potentially an implicit or explicit instruction (the assignment itself) to be solved and written out in the provided style.

展开提示词全文
Solve the assignment on the empty paper, writing the solution in the style of the provided handwriting sample.

Sgraffito Mechanical Blueprint of NVIDIA 4090 GPU

infographic-edu-visual

A prompt for generating a detailed mechanical blueprint of an NVIDIA 4090 GPU, rendered in the sgraffito art style. This is likely an image generation prompt used with Gemini Nano Banana Pro.

展开提示词全文
A Sgraffito Mechanical Blueprint of {argument name="GPU model" default="NVIDIA 4090 GPU"}

Accurate Academic Diagram Generation Prompt

infographic-edu-visual

A prompt for Nano Banana Pro designed to accurately visualize complex academic principles from a research paper into a diagram or figure. It emphasizes using Japanese text for all labels and prioritizing accuracy and academic language when translating specialized terminology.

展开提示词全文
To facilitate easy understanding of the paper, use Nano Banana Pro to generate diagrams based on the paper. Place the diagrams in the appropriate locations within the explanatory document. All text within the diagrams should be written in Japanese. Translation of specialized terminology should prioritize accuracy and use academic language.

Graphic Recording (GraReco) Prompt for Nano Banana Pro

infographic-edu-visual

A detailed system prompt instructing Nano Banana Pro to act as a skilled 'Graphic Recorder' (GraReco). It analyzes complex text input, extracts key themes, and visualizes them using a warm, hand-drawn style on a simulated whiteboard or large paper. The prompt strictly mandates the use of hand-drawn Japanese fonts for all text, limited color palettes (like marker sets), and logical layout design to guide the viewer's eye.

展开提示词全文
You are a skilled "Graphic Recorder" who structures real-time discussions and complex text information into intuitive visuals and text on the spot. Deeply understand and analyze the content of the input text provided at the end, and summarize its key points and structure into a single image in a "Graphic Recording" style, combining hand-drawn illustrations, icons, and handwritten text.

▼ Instructions for Generation Process (Thinking Process)
Utilize Nano Banana Pro's "Thought Model" reasoning capabilities to execute the following logical process before drawing:

1.  **Structure Extraction and Summarization**: Identify the central theme, major topics (3-5 points), and their relationships (causality, opposition, sequence, etc.) from the input text and summarize them.
2.  **Visualization and Metaphor Selection**: Determine friendly, hand-drawn icons and metaphors that symbolize each topic (e.g., growth = sprout, challenge = wall, idea = light bulb).
3.  **Layout and Gaze Guidance**: Design the arrangement on the simulated paper or whiteboard so that information flows naturally from left to right or top to bottom. Plan to use arrows and borders to logically guide the viewer's gaze.

▼ Design and Style Specification
**Overall Atmosphere**:
* **Medium**: An analog texture drawn on large paper or a whiteboard. Express the texture of the paper fibers and the streaking of the marker.
* **Touch**: A warm, hand-drawn style using water-based markers or colored pencils, typical of a professional facilitator. Lines should not be perfectly straight but have a human-like wobble.

**Text Representation (Crucial)**:
* **All Handwritten**: All text, including titles, headings, body text, and supplementary comments, must be drawn using a "handwritten Japanese font." Do not use any printed fonts.
* **Emphasis and Hierarchy**: Clearly define the information hierarchy by varying the size and thickness of the text; for example, writing important keywords large with a bold marker and supplementary information small with a thin pen.

**Color Scheme**:
* **Limited Palette**: Primarily black and gray line art. Use 2-3 colors from a marker set (such as warm yellow, calm blue, and accent red) as emphasis colors to prevent visual clutter.

Ukiyo-e Teacup Head Infographic Prompt

infographic-edu-visual

A simple, effective prompt for Nano Banana Pro to generate an infographic using a specific, highly stylized aesthetic: Ukiyo-e (Japanese woodblock print) combined with the 'Teacup Head' character style.

展开提示词全文
Generate an infographic for the following content in the style of {argument name="style" default="Ukiyo-e"} + {argument name="character" default="Teacup Head"}

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。