← 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

Hand-Drawn Isometric Schematic Diagram Prompt

infographic-edu-visual

A prompt template for Nano Banana Pro used to create a hand-drawn, isometric schematic diagram of any object or concept, with examples provided for the principle of aircraft takeoff and the inside of the human brain.

展开提示词全文
Nano Banana Pro, Create a hand drawn isometric schematic diagram of {argument name="Object or Concept" default="the principle of aircraft takeoff"}

Structured Prompt for Archaeological Dig Scene with 3D Data Overlay

infographic-edu-visual

A highly structured JSON-formatted prompt for Nano Banana Pro detailing an archaeological scene. The prompt specifies the setting (dusty desert trench), subject (based on an uploaded image, crouching, excited), technical style (5:4 portrait, documentary, high contrast), and a unique element: a semi-transparent 3D timeline and data projection emanating from a recently uncovered ceramic pot.

展开提示词全文
{
 "promptDetails": {
 "description": "An archaeological dig scene where the subject is viewing a 3D timeline and data overlay projected onto a recently uncovered artifact.",
 "styleTags": [
 "Archeology",
 "Earthy Textures",
 "Academic/Documentary",
 "Dry and Dusty"
 ]
 },
 "scene": {
 "background": {
 "setting": "An active archaeological trench in a dusty, sun-baked desert environment",
 "details": "Brushes and small tools visible, measuring tapes and grid markers in the soil, exposed layers of earth, a recently uncovered ceramic shard/pot."
 },
 "subject": {
 "description": "The person defined by `[UPLOADED IMAGE]`, wearing field clothes and perhaps a brimmed hat, looking excited and careful.",
 "pose": "Crouching down in the trench, holding a small brush near the artifact, looking intently at the projection.",
 "focus": "The artifact and the projection are the key points of visual interest."
 }
 },
 "overlayObject": {
 "type": "3D Timeline and Data Projection",
 "relationshipToEnvironment": "A semi-transparent, three-dimensional graphic emanating directly from the surface of the ceramic pot, showing its timeline.",
 "transform": "A series of floating text labels and lines showing dates and cultural periods, seemingly anchored to the artifact.",
 "surfaceInteraction": "Faint, slightly flickering orange/white text and lines that look 'hot' or energized, contrasting with the dry earth.",
 "components": {
 "artifactID": "{argument name=\"artifact ID\" default=\"Vessel Shard K-203\"}",
 "dating": "{argument name=\"dating\" default=\"Estimated C. 500 B.C. (Early Iron Age)\"}",
 "position": "Emanating from and hovering around the pot."
 }
 },
 "technicalStyle": {
 "aspectRatio": "5:4 (Portrait)",
 "photographyStyle": "Documentary, High Contrast",
 "camera": {
 "shotType": "Close-Up",
 "angle": "Low to the ground, capturing the detail of the soil and the artifact.",
 "depthOfField": "Shallow, focusing tightly on the subject's hands, the artifact, and the projection."
 },
 "lighting": {
 "type": "Harsh, Overhead Daylight",
 "description": "Strong, high-angle sun casting short, dark shadows, emphasizing the dry, dusty nature of the scene."
 },
 "color": {
 "palette": "Monochromatic earth tones (browns, tans, desaturated oranges), contrasted by the bright white/orange of the projection."
 }
 }
}

Evolutionary Bridge Cinematic Shot Prompt

infographic-edu-visual

A prompt designed to create a cinematic, high-resolution shot of a single, winding bridge that seamlessly transitions through different architectural eras—from Roman stone to futuristic composite material—with era-appropriate travelers and weathering, set in a misty valley with soft morning light.

展开提示词全文
A cinematic shot of a single, winding bridge stretching into the distance. The architecture transitions seamlessly along its length: starting as Roman stone, becoming a medieval drawbridge, then a Victorian iron truss, and finally a futuristic composite material. Each section has era-appropriate travelers and weathering. Morning mist fills the valley below, with soft light breaking through clouds. 8K.

Isometric Schematic Diagram of Notre Dame Prompt

infographic-edu-visual

A simple text prompt instructing the AI to create a hand-drawn isometric schematic diagram of the Notre Dame cathedral.

展开提示词全文
"Nano Banana Pro, Create a hand drawn isometric schematic diagram of the notre dame"

Novel Optical Illusion Generation

infographic-edu-visual

A meta-prompt challenging the AI to generate a completely new optical illusion. It requires the AI to analyze the elements of typical illusions, avoid common tropes (impossible structures, faces/vases), and base the novel illusion around the specific word 'fofr'.

展开提示词全文
Consider the elements of typical optical illusions. Think about all the different types and how they work. Now make an image that is a novel optical illusion. Avoid the common tropes like impossible structures, steps, faces and vases. Surprise me. The illusion should be based around the word fofr.

Loch Ness Monster Visual Description and Generation

infographic-edu-visual

A meta-prompt instructing the AI to first synthesize all known information about the Loch Ness Monster into a detailed visual description, and then use that description to generate a photorealistic, landscape-oriented image of the creature.

展开提示词全文
convert all you know about Loch Ness Monster into a visual description of how it would look like and create a photorealistic image in landscape mode. Write a clear and concise well detailed prompt first and then generate image please.

Safety Hazard Analysis and Visualization

infographic-edu-visual

A prompt designed for an AI capable of image analysis and re-generation. It asks the AI to analyze a provided image for specific safety hazards (fire, tripping, electrical), regenerate the room in black and white, and overlay bright neon red bounding boxes and text labels identifying each risk found.

展开提示词全文
Analyze this image for safety hazards. Re-generate this exact room in black and white, but overlay bright NEON RED bounding boxes around every safety risk you find. Specifically look for: fire risks, tripping hazards, and electrical issues. Label each red box with a small text tag explaining the danger (e.g., 'Fire Risk').

Scientific Ultra-Macro Insect Capture Prompt

infographic-edu-visual

An extremely detailed, technical prompt designed for generating a hyper-realistic, scientific ultra-macro photograph of a predatory wasp carrying a bright green caterpillar. It specifies the goal, subject, pose, framing, and includes meticulous camera and post-processing settings (apochromatic macro lens, f/11, 1/8000 shutter, cross-polarized lighting, focus stacking) to achieve entomology documentation realism.

展开提示词全文
"[GOAL] Hyper-realistic ultra-macro insect capture in mid-air
[SUBJECT] predatory wasp carrying a bright green caterpillar
[POSE/STATE] wings stretched mid-beat, prey gripped tightly, both suspended in motion
[FRAMING] full-body insect profile, isolated; subject centered with generous negative space
[LENS] apochromatic macro 100mm, 2:1 magnification
[APERTURE] f/11 deep global sharpness
[SHUTTER] 1/8000 freeze-motion
[LIGHTING] cross-polarized dual-diffused flash; wrap-around softbox; specular-suppression; rim accent camera-right 10°
[COLOR] natural crimson-amber chitin; neon-green larvae tones; neutral matte background gradient
[MATERIALS] chitin texture with micro-pitting; translucent wing membranes with vein fidelity; caterpillar skin with SSS and fine ridges
[FX] none; zero motion blur; no halos; no glow
[DOF] deep-plane focus stacked (40+ slices)
[ENV/BG] seamless monotone backdrop, soft bokeh compression, no environmental clutter
[RENDER] scientific-macro discipline; entomology documentation realism
[POST] deconvolution sharpening; chromatic-aberration removal; micro-contrast S-curve; artifact-free edges; grain <3%
[CONSTRAINTS] AR 16:9; forbid stylization, color bleed, softness, fictional anatomy"

Behind-the-Scenes Generation Prompt

infographic-edu-visual

A simple, direct prompt used to generate a 'behind-the-scenes' image based on a provided reference scene, specifically demonstrated here using a scene from the movie 'The Exorcist'.

展开提示词全文
create the behind-the-scenes of this scene from The Exorcist

Watercolor Travel Map Illustration Prompt

infographic-edu-visual

A simple prompt instructing the model to generate a watercolor travel-map illustration of cities.

展开提示词全文
Watercolor travel-map illustration of Cities

Two-Step Tier List Generation Prompt

infographic-edu-visual

A two-part prompt sequence used to generate a visual tier list. The first prompt generates the structured JSON data for the tier list, and the second prompt uses that data to generate the corresponding image in a classic style with representative thumbnails.

展开提示词全文
Make a json of a tier list (S-F scale) for: {argument name="category" default="[*insert-here*]"}

Now generate image with the classically seen style/color scheme and representative thumbnail images for each list item

Prompt for clearing handwritten answers from a test image for reuse

infographic-edu-visual

This prompt is designed for use with an AI tool like Nano Banana Pro to process an image of a completed test paper. The goal is to remove all handwritten answers, specifically text within parentheses, squares, and red circles (like corrections or scores), leaving a blank test template that can be solved again repeatedly.

展开提示词全文
I want to solve this test again, so please reliably delete the red circles and all handwritten characters in the answer fields within parentheses or squares, and make them blank.

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。