← 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

Deconstructed Ingredients Visualization

infographic-edu-visual

A mathematical-style prompt for Nano Banana to visualize the deconstructed ingredients of a famous international dish, combining elements like miniature toy chefs, floating AR UI panels, and radar charts on a slate serving board.

展开提示词全文
( Deconstructed_Ingredients_{argument name="dish name" default="[DISH_NAME]"} * 1.5 ) + 
( Miniature_Plastic_Toy_Chef * 1.2 ) + 
( Floating_Frosted_Glass_AR_UI_Panels * 1.5 ) + 
( Flavor_Profile_Radar_Charts * 1.0 ) + 
( Slate_Serving_Board * 1.0 ) +
( Blurred_Cookbook_Background_{argument name="dish name 2" default="[DISH_NAME]"} * 0.8 ) +
( Pure_White_Studio_Void * 1.0 ) - 
( Human_Sized_Chef / 2.0 ) - 
( Messy_Plating / 2.0 )

Caravaggio Meets National Geographic Dissection

infographic-edu-visual

A highly descriptive and conceptual prompt for Nano Banana Pro, instructing the generation of a dissected natural object (specimen) lit dramatically like a Caravaggio painting but with the detail of National Geographic photography. It requires specific text overlays and a mood blending science and sacred beauty.

展开提示词全文
[NATURAL OBJECT] dissected as if by a master naturalist who found it in the wild. Split and pinned open like a specimen, but lit as if Caravaggio worked for National Geographic. Every internal structure glowing with its own material truth. Cross-section so sharp it feels violent. Interior so beautiful it feels sacred. The full object present, one half intact, one half opened to its core, every layer at the resolution of obsession. Background: pure black velvet. The object floats in it like something precious and dangerous. Labels pressed close, handwritten-weight serif, never floating: "[STRUCTURE]" / "[MATERIAL TRUTH]" / "[AGE OR SCALE]" "[OBJECT] DISSECTED" title in warm ivory caps, upper left. "[One line that makes you lean closer]" italic beneath. Mood: Audubon illustration meets Caravaggio meets the most beautiful science photograph ever taken. 4K, specimen lighting, extraordinary interior detail, nothing clinical, everything alive.

Slow Motion Pour Food Photography Prompt for Nano Banana 2

infographic-edu-visual

A detailed prompt for Nano Banana 2 designed to generate ultra high-speed food photography, freezing a dramatic liquid pour over a dish. It specifies cinematic lighting, hyperreal textures, and editorial typography, mimicking the style of Albert Watson and Harold Edgerton.

展开提示词全文
[DISH] at the precise moment of a dramatic [LIQUID] pour in ultra high-speed photography, liquid cascade frozen mid-fall in perfect clarity. Hero [DISH] center on matte [COLOR] surface, [LIQUID] pouring from above in one cinematic ribbon catching warm single-source light, splitting and branching into suspended droplets and threads as it hits the surface. Splatter crown frozen at moment of impact, droplets suspended in perfect arcs. Every surface texture hyperreal: glistening, steaming, sauce pooling in slow motion. Each element labeled with ultra-thin lines in clean uppercase: "[INGREDIENT] [descriptor]". Dish name in elegant editorial typography: "[DISH NAME]". Subtitle: "[TAGLINE]". Mood: Albert Watson food photography meets Harold Edgerton fluid dynamics meets Michelin-star editorial. 4K, tack sharp every thread and droplet, warm single-source light, extraordinary and craveable.

Technical Blueprint of an AI GPU Cluster

infographic-edu-visual

A highly detailed prompt for Gemini Nano Banana Pro to generate a futuristic, cinematic image of a technical blueprint transforming into a photorealistic, self-assembling AI GPU cluster on a polished brass drafting table, emphasizing technical details, lighting, and composition.

展开提示词全文
A detailed technical blueprint of a high-performance AI GPU cluster placed on a polished brass drafting table, with a photorealistic miniature AI server system self-assembling from it — multiple GPU accelerator units (sleek black and metallic modules with neon green accents) rising from the dimension lines, high-speed interconnect bridges threading through the tolerance annotations, and dense compute nodes forming from the grid layout.

Stacks of GPU cards slide into server chassis above the parts list, each unit locking in with precision. NVLink-style connectors and high-bandwidth interconnects assemble seamlessly between GPUs, forming a powerful parallel compute network. Rack-mounted AI servers emerge vertically, with layered compute blades building upward in perfect alignment.

A liquid cooling system forms from exploded-diagram callouts — transparent cooling pipes with glowing coolant flowing through them, cold plates attaching to GPUs, and radiators assembling with high-performance fans. Heat dissipation fins and airflow channels dynamically shape around the system.

A tiny engineer in futuristic protective gear stands on a GPU module inspecting circuits with a holographic diagnostic interface, while another miniature technician connects high-speed data cables into a switch unit. Fiber optic lines glow faintly, representing active data transfer.

Functional details illuminate — GPU core lights pulsing softly, status LEDs blinking in synchronized patterns, data streams visualized as glowing lines moving between nodes, and monitoring panels activating during assembly.

Signature tools of the trade — precision screwdriver, thermal paste applicator, anti-static tools, fiber connectors, and a digital diagnostic tablet — rest across the blueprint’s title block, partially integrated into the scene.

All elements grow organically from the blueprint like a 3D mechanical diorama — circuit traces rising from printed schematics, GPU modules emerging from drawn outlines, cables threading through pencil grid lines. Seamless transformation from 2D blueprint into a fully operational AI infrastructure.

LIGHTING:
Soft studio lighting combined with strong neon green and cool blue glows from GPUs and data pathways. Subtle reflections from the brass surface and volumetric light enhancing depth.

CAMERA & LENS:
Shot on a full-frame camera, 35mm lens. Slight low-angle perspective to emphasize scale and power. Cinematic depth of field with focus on central GPU cluster.

COMPOSITION:
Vertical 2:3 format. Central stacked GPU cluster rising upward with symmetrical balance. Clean negative space around edges with layered depth.

STYLE & MOOD:
Futuristic, cinematic, high-end AI infrastructure aesthetic inspired by NVIDIA design language. Powerful, clean, and cutting-edge.

DETAILS:
Ultra-detailed textures — matte black metal, glowing accents, micro circuitry, cooling liquid reflections, cable braiding, LED indicators. 8K resolution, HDR,

2x2 Grid Pop-Up Cookbook Diorama Prompt for Nano Banana

infographic-edu-visual

A structured instruction set for Nano Banana to generate a 2x2 grid, where each panel represents an open book spread for a different country's dish, featuring 2D vintage sketches on the left page and a 3D pop-up diorama of the finished dish on the right, all styled as a cohesive atlas series.

展开提示词全文
<instructions>
[Use the UNIVERSAL WRAPPER above exactly as-is.]

If input includes ingredients, pick 4 distinct countries with famous dishes that fit those ingredients (hidden gems welcome). Output one 2x2 grid: each panel shows an open book spread for that country.

Per panel:
- Left page: 2D vintage sepia sketches (timeline/illustrated recipe flow, minimal text).
- Right page: 3D pop-up diorama of the finished steaming dish emerging from the page.
- A tiny chef mini stands beside the dish.
- All 4 books look like one cohesive atlas series.
- Only readable text: engraved plate “Dish ({argument name="country name" default="Country"})”.

Style: Cinematic top-down lighting emphasizing 2D vs 3D depth, macro detail, cohesive atlas design, clean background, shallow DOF, no logos, no long text.
</instructions>

Augmented Reality UI Overlays on Food Items

infographic-edu-visual

A set of three prompts for Gemini Nano Banana Pro to generate photorealistic POV shots of hands holding food items (dessert, apple, soda bottle) in a supermarket, overlaid with futuristic Augmented Reality (AR) user interfaces displaying nutritional and product data. The prompts specify lighting, depth of field, and UI design style (glassmorphism, tech-inspired).

展开提示词全文
Dessert (AR shopping UI)

POV shot inside a modern supermarket aisle, hands holding a small gourmet dessert with cream and berries, futuristic augmented reality (AR) interface overlay showing calories, sugar, fats, freshness score, expiry date, and recipe suggestions, soft depth of field, cinematic lighting, ultra-realistic, 4K, tech-inspired UI, clean glassmorphism design

⸻

2. Apple (AR nutrition UI)

First-person view in a grocery store holding a fresh red apple, augmented reality interface displaying calories, vitamin C, fiber, freshness bar, and recipe ideas, minimal futuristic UI panels floating around the object, bright supermarket lighting, shallow depth of field, hyper-realistic, modern tech aesthetic, 4K

⸻

3. Orange Soda Bottle (AR data UI)

POV shot of hands holding an orange soda bottle in a supermarket aisle, futuristic AR overlay showing calories, sugar content, caffeine level, freshness score, expiry date, and drink recipes, sleek holographic interface, glassmorphism UI, vibrant colors, cinematic lighting, ultra-detailed, photorealistic, 4K

PCB Word Art Schematic for 'Tesla'

infographic-edu-visual

A technical prompt for Nano Banana Pro using weighted terms (::) to generate a 2D schematic illustration of the word 'Tesla' constructed entirely from printed circuit board (PCB) traces. It specifies monochrome coloring, technical vector style, and flat lighting, while using a negative prompt to exclude realistic textures or colors.

展开提示词全文
Anchor: The word "{argument name="word to construct" default="Tesla"}" :: constructed entirely from printed circuit board traces, where each letterform is a functional-looking PCB layout — solder pads as terminals, vias as joints, trace paths forming the strokes ::4 Morphology: Technical PCB illustration. Letter strokes are traces of varying widths. Circular vias punctuate stroke junctions. Solder pad rectangles anchor stroke terminals. The letters read as living circuit diagrams. Monochrome technical vector ::3 Material Physics: Jet black trace lines on white substrate, exposed copper-pad circles with concentric detail rings, uniform stroke weight with deliberate corner chamfers (45°) ::3 Illumination: Flat technical illustration lighting, no depth, pure 2D schematic clarity ::2 Render Stack: Electronics schematic aesthetic, hardware documentation style, Gerber file visual output ::1 Negative: [Silhouette shapes, actual electronic components, chip illustrations, realistic PCB green color, perspective, photographic textures, solder reflections] ::-1

Template for generating a fictional textbook page

infographic-edu-visual

A reusable template prompt for Nano Banana 2 designed to generate a page from a fictional textbook. The user can customize the world setting and subject, ensuring the content is accurate Japanese, avoids font corruption, and is presented as a realistic photo of an open textbook viewed from above.

展开提示词全文
Create a page from a textbook on "{argument name="subject" default="Biology"}" used in a school in a "{argument name="worldview" default="Fantasy World"}".
The content of the textbook must not be based on the real world, but must strictly adhere to the specified worldview. The content should be written in accurate Japanese, avoiding duplication of content and font corruption. The composition is a realistic photo of an open textbook taken directly from above, not an illustration.

Futuristic Holographic Burj Khalifa Blueprint

infographic-edu-visual

A detailed prompt for generating a futuristic, cinematic image of the Burj Khalifa architectural blueprint projected as a glowing, actively constructing hologram above a high-tech glass table. The prompt specifies the transition from wireframe to photorealistic structure, lighting (neon blue/cyan), and environment (minimal architectural lab).

展开提示词全文
CONCEPT:
A futuristic architectural blueprint of the Burj Khalifa projected as a glowing hologram, actively constructing itself in mid-air through robotic precision and digital intelligence.

SUBJECT:
A semi-transparent holographic version of the Burj Khalifa floating above a sleek glass smart table. The lower portion appears as a glowing blue wireframe blueprint, while the upper portion transitions into a fully photorealistic skyscraper with reflective glass panels and metallic structure as it builds itself in real-time.

ENVIRONMENT:
A high-tech architectural lab with a dark, minimal interior. The blueprint originates from a glossy black glass table embedded with touch controls, glowing UI panels, and soft neon edges. Subtle reflections of the hologram appear on the table surface. Background is clean, futuristic, and slightly blurred.

STRUCTURAL DETAILS:
The central spire rises as glowing gridlines before solidifying into steel and glass  
Tiered setbacks of the tower assemble through hovering robotic drones  
Glass facade panels lock into place with precise alignment and reflections  
Laser beams scan and map each level during construction  
Small AI drones orbit around the structure, actively building and welding components  
Materials transition from holographic light into real textures — polished glass, steel beams, and concrete core  
Floating UI overlays show measurements, grids, and rotating architectural schematics

VISUAL MECHANIC:
The blueprint exists in layered form — base is a glowing grid, mid-layer is a semi-transparent wireframe, and top layer is fully realistic. Certain sections flicker between hologram and solid material, emphasizing the transformation.

LIGHTING:
Dark environment with strong neon blue and cyan holographic glow. Subtle rim lighting created by reflections from the hologram. Volumetric light beams and soft particles enhance depth.

CAMERA & LENS:
Shot on a full-frame camera, 35mm lens. Slight low-angle perspective to emphasize scale and height. Sharp focus on the hologram core with slight background blur.

COMPOSITION:
Vertical 2:3 format. The Burj Khalifa hologram is centered, rising upward. UI elements orbit symmetrically around it. Clean negative space enhances the futuristic aesthetic.

STYLE & MOOD:
Futuristic, cinematic, high-tech, and minimal. Feels like advanced AI-driven architecture and innovation. Clean, premium, and visually striking.

DETAILS:
Ultra-sharp holographic lines, glowing particles, realistic glass reflections, smooth transitions between digital and physical materials, micro UI details, 8K resolution, HDR, cinematic color grading with blue/cyan tones and deep contrast.

NEGATIVE PROMPT:
cluttered environment, low detail, dull lighting, messy UI, cartoon style, distorted structure, blurry hologram, watermark

The Naturalist Dissection Prompt

infographic-edu-visual

A detailed Nano Banana 2 prompt for generating an image of a natural object (like a flower or insect) dissected and pinned open like a specimen, rendered with the lighting style of Caravaggio and the detail of National Geographic photography, emphasizing the contrast between the intact and opened halves.

展开提示词全文
[NATURAL OBJECT] dissected as if by a master naturalist who found it in the wild. Split and pinned open like a specimen, but lit as if Caravaggio worked for National Geographic.
Every internal structure glowing with its own material truth. Cross-section so sharp it feels violent. Interior so beautiful it feels sacred. The full object present, one half intact, one half opened to its core, every layer at the resolution of obsession.
Background: pure black velvet. The object floats in it like something precious and dangerous.
Labels pressed close, handwritten-weight serif, never floating: "[STRUCTURE]" / "[MATERIAL TRUTH]" / "[AGE OR SCALE]"
"{argument name="object" default="[OBJECT]"} DISSECTED" title in warm ivory caps, upper left. "{argument name="line" default="[One line that makes you lean closer]"}" italic beneath.
Mood: Audubon illustration meets Caravaggio meets the most beautiful science photograph ever taken. 4K, specimen lighting, extraordinary interior detail, nothing clinical, everything alive.

Complex Machine Deconstruction Blueprint Prompt

infographic-edu-visual

A complex, multi-stage Nano Banana prompt designed to generate a 'Kinetic Blueprint' photograph of a complex machine (like a Space Shuttle) being deconstructed into three assembly phases, displayed within partially unfolded triangular acrylic wedges on a drafting table, emphasizing technical art and macro rendering.

展开提示词全文
<instruction>
 
Input A is a Complex Machine (e.g., {argument name="machine type" default="A Space Shuttle"}, A Grand Piano, A Clockwork Watch).
Deconstruct into   3 Assembly Phases  :
   Phase 1:  Raw chassis/frame.
   Phase 2:  Internal gears/wires.
   Phase 3:  Finished exterior.
2. Container (The Geometric Unfold):
Goal: "Kinetic Blueprint" Photography.
The Object: A series of Triangular Acrylic Wedges attached to a central hinge, opening like a blooming flower or a tool-kit.
The Layout: The wedges are partially unfolded across a drafting table surface.
3. The Dioramas (The Exploded View):
Internal Content: Each wedge holds a different "Phase" of the machine.
Visual Link: Real copper wires or brass chains physically cross the gaps between the acrylic wedges, "connecting" the assembly line.
4. Visual 
Background: A cluttered workshop desk with blueprints and calipers.
Lighting: Hard side-lighting to cast shadows of the internal gears through the clear acrylic walls onto the table.
Output: ONE image, 16:9 Aspect Ratio, 3D Macro Render, "Technical Art" aesthetic.
</instruction>

Four-Panel Manga: The Legend of the 5000 Yen Cost

infographic-edu-visual

This is the title and key phrases used to generate a four-panel manga image using Nano Banana Pro, focusing on the theme of 'The Legend of the 5000 Yen Cost' and the high-profit margin of a 500,000 yen champagne tower costing only 5,000 yen.

展开提示词全文
Title
The Legend of the 5000 Yen Cost

The cost of a 500,000 yen champagne tower is
5,000 yen?

Profit margin over 90%

What is this?

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。