← 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

Circular Language Infographic

infographic-edu-visual

Creates an astronomical-style infographic mapping the world's languages by endangerment status in concentric rings.

展开提示词全文
Produce a circular infographic — like an astronomical orrery — with {argument name="language count" default="7,000"} of the world's languages arranged in concentric rings by endangerment status: extinct at the center, critically endangered, endangered, vulnerable, safe at the outer ring. Each language represented by a small typographic tile showing its name in its own native script. Color gradient from deep red (extinct) to vivid green (safe). The rings are labeled with speaker population ranges. Five spotlight callouts pull out a specific dying language and show its geographic origin on a miniature globe, with one surviving sentence rendered in that script.

Vertical Exploded Food Infographic

infographic-edu-visual

A professional studio-style prompt for creating hyper-realistic vertical exploded infographics of food items or products, featuring clean labeling and macro photography aesthetics.

展开提示词全文
Hyper-realistic exploded vertical infographic composition of a {argument name="food or product" default="gourmet cheeseburger"}. All ingredients evenly spaced and perfectly aligned vertically. {argument name="background color" default="Warm yellow"} seamless studio background, soft commercial food lighting, subtle realistic shadows under each floating element, ultra-sharp focus, DSLR macro food photography, premium fast-food ad aesthetic, 8K. Clean infographic text labels with thin pointer lines.

The Food Galaxy: Cosmic Indian Street Food Solar System

infographic-edu-visual

A creative and detailed prompt for Nano Banana 2 to generate a surreal, photorealistic image of Indian street food floating in deep space, where each food item represents a celestial body (e.g., tandoori roti as the sun, golgappa as a planet, samosas as asteroids). The prompt specifies lighting, background elements (spice nebula, lassi Milky Way), and style.

展开提示词全文
Create a cosmic/space scene where various Indian street foods are floating in deep space as if they are planets, moons, and celestial objects in a delicious galaxy.

THE FOOD SOLAR SYSTEM:
- CENTER (Sun): A massive round tandoori roti, glowing from within like a star, with charred spots resembling sunspots, radiating warm golden light outward
- PLANET 1 (closest): A perfect round golgappa/pani puri — crispy shell glistening, filled with spiced water visible through the opening. Tiny orbit ring of sev and chutney droplets.
- PLANET 2: A round vada (medu vada) as a donut-shaped planet with a ring system made of coconut chutney
- PLANET 3: A plate of round gulab jamuns as a cluster of sweet brown planets with syrup nebula around them
- ASTEROID BELT: Dozens of floating samosas, pakoras, and bhel pieces scattered in a ring
- PLANET 4 (gas giant): A huge round dahi vada — white yogurt surface like a cloudy gas giant, with tempering (tadka) marks resembling Jupiter's storms
- COMET: A kebab skewer streaking across the scene with a trail of spice smoke and sparks
- MOON: A round idli orbiting the dahi vada planet
- NEBULA: A colorful cloud of turmeric (yellow), chili (red), and coriander (green) powders mixing in space, forming a stunning spice nebula

BACKGROUND:
- Deep space black with thousands of tiny stars (mustard seeds and cumin seeds floating as stars)
- Distant galaxies made of swirling masala powder
- The Milky Way visible but made of a stream of white lassi/buttermilk

LIGHTING:
- The tandoori roti "sun" provides warm orange light illuminating nearby foods
- Each food item has its own subtle glow — the hot items emit warm light, the cold items (lassi, curd) emit cool blue light
- Dramatic space lighting: stark bright highlights, deep black shadows, no atmosphere

STYLE: Photorealistic food photography meets NASA space photography. Every food item is rendered with appetite-triggering detail — crispy textures, steam, glistening oil, fresh garnishes — but floating in actual outer space with real stars and cosmic phenomena. This surreal combination is the kind of image people share saying "this is the most Indian thing I've ever seen." 8K resolution.

Diagram Style Prompts for Nano Banana 2

infographic-edu-visual

A set of five style templates for generating stable, structured diagrams using Nano Banana 2. Users can replace the content within brackets to create different types of visual aids, such as menu-style lists, prescription forms, boarding passes, dashboard UIs, and diagnostic flowcharts.

展开提示词全文
① Menu Style
Create a diagram of "5 selected {argument name="side job skills" default="skills to earn money with side jobs"}" in the style of a Japanese restaurant menu. Use vertical writing, brush strokes, and a Japanese paper-like background.

② Prescription Style
Create a diagram of "{argument name="AI usage" default="correct way to use AI"}" in the style of a medical prescription. Include an Rx mark, white background, and medical blue color.

③ Boarding Pass Style
Create a diagram of "{argument name="departure point" default="life without AI"} → {argument name="destination" default="life after AI utilization"}" in the style of an airline boarding pass. Include departure point, destination, and a barcode.

④ Dashboard UI Style
Create a diagram comparing the performance of "{argument name="comparison subjects" default="ChatGPT vs Claude"}" in the style of a dark mode dashboard UI. Include KPI cards and graphs.

⑤ Diagnosis Chart Style
Create a diagnosis chart for "{argument name="AI tool" default="AI tool"}" that suits you, in the style of a Yes/No branching flowchart. Include arrows and color-coded nodes.

Artemis II Mission Journal Diorama

infographic-edu-visual

A complex, structured prompt for Nano Banana using Python-like class definitions to generate a hyper-detailed diorama visualization of an astronaut's mission-planning journal for the Artemis II mission, focusing on the transition of 2D sketches into physical 3D miniatures.

展开提示词全文
do this for Artemis II mission: class Artemis_Journal_Diorama:
    def __init__(self, subject="Artemis II Mission"):
        # AI infers the correct materials, textures, and desk environment
        self.stage = "AI‑inferred astronaut’s mission‑planning journal lying open on an AI‑inferred technical workstation."
        self. lighting = "AI‑inferred mixed illumination: task‑lamp warmth + cool instrument‑panel spill."

    def semantic_2D_to_3D_growth(self):
        # AI infers what '2D mission sketches' look like for this subject
        page_texture = (
            f"AI‑inferred handwritten notes, trajectory arcs, module schematics, "
            f"and mission annotations related to {self.subject}, rendered as precise 2D graphite diagrams."
        )

        # AI infers what physical 3D elements should emerge from those sketches
        diorama_pop = (
            f"2D mission diagrams transition into physical 3D miniatures: "
            f"AI‑inferred spacecraft components, crew figures, lunar geometry, "
            f"and mission‑specific hardware rising seamlessly from the paper."
        )

        return [page_texture, diorama_pop]

    def scatter_ephemera(self):
        # AI infers mission‑relevant desk objects without hard‑coding categories
        return infer_aerospace_ephemera(self.subject)
        # Examples (AI‑inferred, not fixed): mission patches, navigation tools,
        # micro‑scale lunar models, printed telemetry, procedural checklists,
        # archival headlines, engineering pencils, etc.

render(Artemis_Journal_Diorama())

Image Redrawing and Style Transfer Prompt

infographic-edu-visual

A prompt designed for Nano Banana to analyze two figures (Figure 1 for style, Figure 2 for content) and redraw Figure 2 in the style of Figure 1, placing both the original Figure 2 and the redrawn version side-by-side on a white background without showing the logo.

展开提示词全文
Carefully study Figure 1, and redraw Figure 2 according to its requirements. Place Figure 2 and the redrawn version on the left and right sides of the same white background image, ensuring the logo is not visible.

Cities as Kinetic Sculptures Grid

infographic-edu-visual

A prompt for generating a 2x2 grid of four different famous cities transformed into unique, looping kinetic sculptures. It specifies the materials (brass, glass, polished wood), the mechanisms for each city type (vertical skyline, light grid, rolling waves, spinning towers), and the museum gallery setting and lighting.

展开提示词全文
A 2x2 grid of 4 random famous cities turned into looping kinetic sculptures on museum plinths
[Top Left: random real European city as a vertical kinetic skyline with moving trams and tiny lights]
[Top Right: random real Asian megacity as a multi-layered kinetic light grid with sliding blocks]
[Bottom Left: random real coastal city with rolling wave mechanisms and rotating landmarks]
[Bottom Right: random real desert or inland city with lifting arms and spinning towers]
Photoreal miniature kinetic sculptures made of brass, glass, and polished wood, subtle motion implied by blurred rods and tracks, illuminated display plinths in a gallery setting, soft museum lighting, gentle reflections on the floor, 60mm perspective for elegant compression, shallow depth of field isolating each sculpture, warm white seamless backdrop, crisp focus on intricate mechanics.

Medieval Altarpiece Display of Ghormeh Sabzi

infographic-edu-visual

A complex, multi-panel prompt designed to visualize an international dish (Ghormeh Sabzi) as a medieval altarpiece. It details the structure of the three panels, requiring elements like ingredient specimens, a 3D pop-up diorama, and preparation steps rendered in a 3D designer toy style, all within a museum exhibition setting.

展开提示词全文
<instruction> Input A is a famous dish (photo or dish name). Analyze the dish's ingredient taxonomy, preparation methodology, cultural preparation setting, and historical documentation style.
Optional Input B is a style reference (3d mod designer toy luxury product packaging).  
Goal: Three-panel folding display (12" tall, 36" wide when open) structured like a medieval altarpiece, with each panel revealing different aspects of the dish's story through museum-quality presentation.
Rules:
Left panel: 15-20 ingredients mounted as specimens in tiny bottles with handwritten Latin/scientific labels
Center panel: 3D pop-up kitchen diorama with cultural figure preparing dish, architectural elements from origin region
Right panel: 6-8 precise preparation steps as 3d mod designer toy style
Closes into protective case with magnetic closure and embossed exterior
Exterior: ornate typography with dish name in gold foil
Small drawer at base containing actual spice sample or "secret ingredient"
Color palette drawn from traditional pottery/textiles of origin culture
Include tiny rolled "scroll" with full recipe in calligraphy
Output: ONE image, 16:9 showing triptych fully opened, shot straight-on, museum exhibition lighting </instruction>

Hyper-Realistic Product Photography and Infographic Prompts for Pepsi

infographic-edu-visual

Two image generation prompts: one for high-quality product photography of a chilled Pepsi can, and another for a hyper-realistic vertical exploded infographic illustrating the ingredients of the soft drink with detailed textures and minimalist styling.

展开提示词全文
Image 1 : High-quality professional product photography of a chilled {argument name="beverage brand" default="Pepsi"} can with condensation water droplets and a refreshing, icy look. The aluminum can appears crisp and glossy with realistic highlights, subtle reflections, and visible cold texture. Shot in a minimalist commercial beverage advertising style against a pure white background with soft natural shadows. Sharp focus, ultra-clean composition, modern aesthetic.

Image 2 : Create a hyper-realistic vertical exploded infographic illustrating the ingredients of a Pepsi soft drink. At the top, clear carbonated water shown as sparkling liquid with fine rising bubbles. Below it, floating white sugar crystals with sharp crystalline texture. Beneath that, a rich amber-brown caramel color layer with glossy, syrup-like depth. Next, a subtle translucent layer representing phosphoric acid with a clean liquid look. Below it, abstract aromatic particles symbolizing natural flavors, light and minimal. Further down, small dark caffeine granules suspended mid-air. At the bottom, a chilled blue aluminum cola can standing upright with realistic condensation droplets and metallic reflections. Pure solid white background, soft studio lighting, subtle realistic shadows under each floating layer, ultra-sharp focus, DSLR macro photography look. Clean minimalist infographic labels with thin pointer lines for each ingredient. Premium beverage advertising aesthetic, modern, photorealistic.

Four-Panel Manga: The Magic of Numbers

infographic-edu-visual

A prompt used with Nano Banana Pro (Gemini 3 Pro Image) to generate a four-panel manga titled 'The Magic of Numbers,' illustrating how financial figures like deficits and budgets can be politically manipulated or reframed as investments.

展开提示词全文
How settlement and budget figures change their appearance through political magic.

Just by rephrasing a deficit as an investment, behold the wonder.

Technical Architectural Blueprint of a Smash Burger

infographic-edu-visual

A highly specific prompt for Nano Banana Pro to generate a technical architectural blueprint of a classic smash burger on deep navy drafting paper. The prompt demands hyperrealistic food rendering with precise measurement lines, stack height callouts, and detailed labels connected by glowing CAD lines, showcasing the model's ability to handle complex text and technical fidelity.

展开提示词全文
Technical architectural blueprint of a Classic Smash Burger on deep navy drafting paper. Hyperrealistic food hero centered-left, dramatically lit from upper left, warm studio spotlight, cross-section view revealing every layer in precise stack order, lacy-edged patties visible in full photorealistic color, cheese mid-cascade, bun toasted golden, sauce pooling at base catching warm light. Blueprint linework in electric blue, precise measurement lines, stack height callouts, patty thickness cross-section, bun diameter diagram, sauce trajectory arc, grid overlay. Labels connected by thin glowing CAD elbow-joint lines, no crossovers: "{argument name="label 1" default="BRIOCHE BUN sesame-crowned, butter-toasted, 11cm diameter"}" "{argument name="label 2" default="SMASH PATTY ×2  80/20 chuck, 85g each, crust-temp 220°C"}"  "{argument name="label 3" default="AMERICAN CHEESE  single-fold melt, 2 slices, full cascade}"  "CARAMELIZED ONION  45min low-heat, moisture-reduced, dark"  "BREAD & BUTTER PICKLE  4mm slice, brine-bright, translucent"  "HOUSE SAUCE  thousand island base, 18g applied, amber". Labels clustered right and top, white Helvetica Neue Light uppercase, thin italic descriptors below. Compass rose bottom-left, scale bar bottom-center, revision block top-right. Title block double-border bottom-right: "DISH: THE SMASH // CLASSIFICATION: AMERICAN CLASSIC // BUILD SPEC: Engineered to be the last burger you ever need." 4K, tack sharp, electric blue linework glowing softly, warm golden burger tones popping against cool navy. Craveable.

Monochrome Engraving Portrait Style

infographic-edu-visual

A detailed prompt for Gemini Nano Banana Pro 2.0 to generate a portrait in the style of a vintage engraving illustration, emphasizing black ink linework, cross-hatching, and classical printmaking aesthetics, based on an uploaded reference photo.

展开提示词全文
Use the Uploaded photo as reference, Vintage engraving illustration style, highly detailed black ink linework, dense parallel hatching and cross-hatching, precise contour engraving lines, woodcut and etching influence, classical printmaking aesthetic, monochrome black and white palette, intricate line density variation to create depth and volume, curved line flow following form anatomy, stippling accents for soft shading, old master engraving technique, baroque illustration feel, antique scientific illustration style, ultra fine (line precision), high contrast with clean negative space, ornamental yet anatomical rendering, hand-engraved texture simulation, timeless classical art style, meticulous craftsmanship, no color, no gradients, purely line-based shading.

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。