← 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

Microscopic View of a Subject

infographic-edu-visual

A concise prompt for Nano Banana Pro designed to generate ultra-realistic, sharp images of common subjects as if viewed through a microscope. It explicitly excludes the microscope apparatus itself, focusing only on the detailed texture of the subject.

展开提示词全文
Imagine a {argument name="subject" default="[subject]"} through a microscope; picture it and create an ultra-realistic sharp image. No microscope parts, only subject.

LLM System Prompt Security Measures (Conceptual)

infographic-edu-visual

This is not an image generation prompt, but a conceptual LLM prompt detailing security measures used by Google Finance, generated by Nano Banana Pro. It outlines various techniques like prompt injection content classifiers, security thought reinforcement, markdown sanitization, and user confirmation frameworks to prevent adversarial attacks and system prompt leakage.

展开提示词全文
Prompt injection content classifiers—Proprietary machine-learning models that detect malicious prompts and instructions within various data formats.

Security thought reinforcement—Targeted security instructions that are added around the prompt content. These instructions remind the LLM (large language model) to perform the user-directed task and ignore adversarial instructions.

Markdown sanitization and suspicious URL redaction—Identifying and redacting external image URLs and suspicious links using Google Safe Browsing to prevent URL-based attacks and data exfiltration.

User confirmation framework—A contextual system that requires explicit user confirmation for potentially risky operations, such as deleting calendar events.

End-user security mitigation notifications—Contextual information provided to users when security issues are detected and mitigated. These notifications encourage users to learn more via dedicated help center articles.

Model resilience—The adversarial robustness of Gemini models, which protects them from explicit malicious manipulation.

2x2 Grid Car Development Phases

infographic-edu-visual

A concise Nano Banana Pro prompt requesting a 2x2 grid illustrating the four distinct development phases of a car: initial sketch, clay model, early prototype, and the final production release.

展开提示词全文
"a 2x2 grid showing the development phases of this car: sketch, clay model, early prototype, 1st final production released car."

Explain Tesla Coil Science

infographic-edu-visual

A text prompt asking the AI to explain the exact science, workings, and reasons behind a plasma glass Tesla experiment, based on an uploaded screenshot from a YouTube channel.

展开提示词全文
draw me the exact science of this and how this experiment works and why.

Labeled Diagram of a Human Cell (Comparison Prompt)

infographic-edu-visual

A prompt used to test the accuracy and detail of image generation models by requesting a fully labeled diagram of a human cell with a minimum of 10 precise and accurate labels. This prompt is used in a comparison context against another model.

展开提示词全文
Create a fully labeled diagram of a human cell with at least 10 labeled elements. Make sure these labels are precise and accurate.

Image Analysis and Correction Tool Description

infographic-edu-visual

This tweet describes a feature of Nano Banana Pro: a game or tool that automatically analyzes and corrects images, suggesting that the prompt itself is a meta-instruction for the AI's function rather than a visual generation prompt.

展开提示词全文
A game that automatically analyzes and corrects images.

Annotating the 'Attention Is All You Need' Paper

infographic-edu-visual

A prompt designed for the Nano Banana Pro model to help users understand the 'Attention Is All You Need' (Transformer) paper. It instructs the AI to provide assistance, circle important content (like figures or formulas), and add explanatory annotations in a hand-drawn style for better comprehension.

展开提示词全文
Please help me understand this paper. Mark important content (figures or formulas) with a circle and add annotations so that I can understand it accurately (in a hand-drawn style).

Anime-style Graphic Recording from Web Search Results

infographic-edu-visual

This prompt is designed for Gemini to first search the web for information about a specific company or topic, and then use Nano Banana Pro to summarize that information into an anime-style graphic recording (grareco), narrated by a fun character like a cat. The process is claimed to take less than a minute.

展开提示词全文
Search the internet for information about {argument name="company name" default="Mizukoshi Co., Ltd."} and create an anime-style graphic recording (grareco) where a {argument name="character" default="cat"} cheerfully explains the findings.

Educational Prompt for High School Math Formulas on a Chalkboard

infographic-edu-visual

A prompt designed to generate a visually appealing and easy-to-understand image of high school entrance exam math formulas written on a chalkboard with color-coding for effective studying.

展开提示词全文
Please summarize the frequently used formulas for high school entrance exam mathematics, written on a chalkboard with chalk.
The formulas should be color-coded for each formula, resulting in a design that is easy to understand at a glance.

Nano Banana Pro Prompt Technique for Beginners

infographic-edu-visual

A prompt technique for using Nano Banana Pro to simplify complex tasks by requesting an explanation in three steps for beginners, which can triple the speed of creating meeting materials.

展开提示词全文
"Explain {argument name="task" default="XX"} in {argument name="number of steps" default="3"} steps for beginners"

Tip for Using Nano Banana Pro: Adding Examples for Better Understanding

infographic-edu-visual

A quick tip for improving the output of Nano Banana Pro by adding the instruction to explain concepts with three concrete examples, leading to a dramatic increase in comprehension.

展开提示词全文
"Explain with {argument name="number" default="3"} concrete examples"

Aerial View of a Film Set

infographic-edu-visual

A prompt to generate an image of a film set from a high-angle aerial perspective, with annotations indicating the film being shot is titled 'If Going to Work Were a Play'.

展开提示词全文
Generate an image of a film set, an aerial high-angle shot of one scene on the set, with annotations indicating the film set is: {argument name="film title" default="If Going to Work Were a Play"}

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。