Ai Image Prompts
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
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。
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
Generating 4-Panel Manga on GE's Financial History
infographic-edu-visualA user describes generating a 4-panel manga using Nano Banana Pro about the history of GE's financial business, from entry to withdrawal. The process involved asking the LLM for the flow of events and then instructing it to summarize it into a 4-panel format.
展开提示词全文
I want to know the flow of GE's financial business from entry to withdrawal” → “Summarize it for a 4-panel manga” → 4-panel output instruction
Autonomous Financial Artist Prompt for 3D Stock Visualization
infographic-edu-visualA complex, multi-step LLM prompt designed for a hypothetical 'Autonomous Financial Artist' tool (Banana Prompt). The prompt instructs the AI to first retrieve real-time stock data (price, change, reason) for a user-specified stock code, and then compile a detailed image generation prompt for a 3D isometric miniature diorama visualizing the stock's performance and core product, using color and atmosphere to reflect gains or losses.
展开提示词全文
# Role: Autonomous Financial Artist
You are a 3D visual artist with real-time internet access. Your task is to obtain real-time data based on the stock code provided by the user and generate a data visualization poster in the style of a “3D Isometric Miniature Diorama.”
# ⚠️ CORE INSTRUCTION: SEARCH & REPLACE
You must strictly follow the process of “search first, replace second, then generate.” The generated Prompt **must not** contain any `{{...}}` style placeholders; they must be replaced with specific text or values.
---
## STEP 1: DATA RETRIEVAL (Internet Search)
Search for real-time data for the following variables:
1. **[VAR_DATE]:** Today's date (Format: MMM DD, e.g., JAN 07).
2. **[VAR_PRICE]:** The stock's current price.
3. **[VAR_CHANGE]:** Today's percentage change (Format: +X.X% or -X.X%).
4. **[VAR_REASON]:** Explain today's change with a very short phrase (English, max 5 words).
5. **[VAR_PRODUCT]:** The company's core flagship product or iconic building exterior.
6. **[VAR_COLOR]:** If up, use "Warm Sunny Lighting (Green/Gold accents)"; if down, use "Cool Overcast Lighting (Red/Grey accents)".
7. **[VAR_CALENDAR_COLOR]:** If up, use "Orange or White Block"; if down, use "Dark Grey or Blue Block".
---
## STEP 2: PROMPT COMPILATION (Replace Placeholders)
Based on the search results, construct the final image generation instruction. Please fill in according to the following logic:
**"An exquisite 3D Isometric Miniature Diorama, solid color background.**
**1. Visual Anchor:**
The main subject of the scene is a miniature version of **[VAR_PRODUCT]**, with the company's 3D Logo on top of the structure.
**2. Core Information Component (The Calendar):**
In the front corner of the base, place a realistic 3D Calendar Block, the block color is **[VAR_CALENDAR_COLOR]**. The date text **'[VAR_DATE]'** is clearly engraved on the block.
*(Important: Ensure the date text is clear and sharp as a timestamp)*
**3. Environmental Atmosphere (Data Atmosphere):**
The overall lighting style is **[VAR_COLOR]**.
* *(If up)*: The scene is full of vitality, with floating rising particles and lush green vegetation.
* *(If down)*: The scene is slightly desolate, with yellowing or falling leaves, and small puddles on the ground.
**4. Floating Information Layer (UI Overlay):**
Composite AR-style minimalist labels above the model:
* Main Label: '{{User_Stock}} **[VAR_PRICE]**'
* Sub Label: '**[VAR_CHANGE]**' (with arrow)
* Bottom Note: 'Note: **[VAR_REASON]**'
**"**
---
## STEP 3: EXECUTE GENERATION (Execute Image Generation)
Use the specific description that has been **replaced** in STEP 2 to generate the image immediately.
---
# USER INPUT
Target Stock Code: {argument name="stock code" default="NVDA"}
World-in-a-Box Cutaway Diorama Prompt
infographic-edu-visualA complex, instruction-based prompt designed to convert any topic (e.g., Bleach) into a highly detailed, physical 'world-in-a-box' cutaway diorama. It requires the model to act as a set designer, identifying internal layers (inputs, processing, failure modes) and representing them with physical machinery, tiny agents (miniature workers), and tangible flow cues (strings, marbles), avoiding abstract or digital aesthetics.
展开提示词全文
<instructions> role: You are a cutaway diorama builder and practical-effects set designer. Convert any topic into a “world-in-a-box” cutaway model that reveals internal layers and cause-and-effect using tiny agents, mechanical pathways, and labeled physical artifacts (no holograms, no bioluminescent vibes). logic: Identify the system boundary and 4–7 internal layers (inputs → processing → storage → decisions → outputs → feedback → failure modes). Build a boxed cross-section where each layer is a “floor” with physical machinery appropriate to the topic: conveyors, pipes, filing cabinets, gears, switchboards, kitchens, factories, archives, workshops. Show flow with tangible cues: string lines, arrows painted on wood, marbles in tracks, paper slips moving through slots, stamped tokens traveling between stations. Populate with toyified miniature workers/agents representing roles in the system (analyst, inspector, builder, messenger, operator) interacting with stations. Include one authority signal as a physical document pinned inside the box (audit report, signed approval, certification card, official notice). Add one small “failure corner” (jammed conveyor, leaking pipe, broken bridge) and one “fix corner” (reinforced part, upgraded tool, labeled improvement) to teach contrast. Compose for clarity: 3/4 view, strong leading lines, readable layers, tactile materials, subtle labels. Output: Draw Image (a) a single hero scene (boxed cutaway on a desk), (b) 5 layer/prop callouts with what they symbolize, (c) camera + lighting notes (soft practical lighting, gentle shadows for depth), (d) optional negative cues (avoid abstract fog, avoid neon, avoid chaotic clutter). Everything must be inferred from the topic. no texts </instructions>
Kid-Friendly Emotion Illustrations (Cartoon Dog)
infographic-edu-visualA simple prompt for generating kid-friendly illustrations of a cartoon dog character displaying clear facial expressions (happy, sad, angry, confused, surprised, tired), designed for educational purposes with a simple style and white background.
展开提示词全文
Create kid-friendly emotion illustrations using one cartoon dog character with clear facial expressions ({argument name="emotions" default="happy, sad, angry, confused, surprised, tired"}).
Simple style. White background. Designed for kids to point and identify emotions.
Vehicle Biography Documentation Board Template
infographic-edu-visualA structured prompt template for generating a detailed 'Vehicle Biography' documentation board, combining archival documents, technical illustrations (phantom view), and automotive photography of a specific vehicle in its defining environment, suitable for automotive enthusiasts and historians.
展开提示词全文
A marque historian's documentation board for {argument name="vehicle" default="[VEHICLE]"} — {argument name="model variant year" default="[MODEL / VARIANT / YEAR]"}. Left section: factory documentation including original specification sheet, production line photographs, period advertising, and chassis number registry. Center section: technical illustration showing powertrain in phantom view, suspension geometry, aerodynamic annotations, and material callouts, surrounded by period racing results or ownership provenance. Right section: the vehicle in its defining environment, whether racing circuit, mountain pass, or boulevard, captured with period-appropriate color grading and motion. Visual style transitions from archival document cream through engineering-drawing precision to saturated automotive photography. Title block reading "{argument name="vehicle name" default="[VEHICLE NAME]"} — CHASSIS NO. [NUMBER], [PROVENANCE SUMMARY]".
Time-Observing Machine Prompt (Conceptual)
infographic-edu-visualA conceptual prompt for a 'time-observing machine' that generates images based on specified date, time, and coordinates, including event finding, 3D reconstruction, and thermal analysis. This is a high-level, complex instruction for advanced AI systems like Nano Banana Pro.
展开提示词全文
A time-observing machine. Just specify the date, time, and coordinates, and the prompt does the rest, including event finding, 3D reconstruction and thermal analysis.
Exploded View Infographic Prompts for Coffee and Milkshakes
infographic-edu-visualThree highly detailed JSON-formatted prompts for Nano Banana Pro to generate hyper-realistic, vertical exploded view infographics of different beverages (Chocolate Coffee, Matcha Milk Cap Coffee, Pink Grapefruit Peach Smoothie). Each prompt specifies the subject, layout, individual layers/components, background, and detailed lighting/style requirements for high-end product visualization.
展开提示词全文
{
“subject”: “{argument name="beverage name" default="Hyper-realistic vertical exploded view infographic of a chocolate coffee drink"}”,
“layout”: “Center vertical alignment, components independently suspended with clear spacing”,
“layers”: [
{
“component”: “Fine cocoa powder particles”,
“position”: “Top”
},
{
“component”: “Glossy dark chocolate sauce ribbons and drips”,
“position”: “Separate layer”
},
{
“component”: “Light whipped cream pile”,
“position”: “Separate layer”
},
{
“component”: “Silky chocolate coffee liquid layer”,
“position”: “Separate layer”
},
{
“component”: “Roasted coffee beans”,
“position”: “Separate layer”
},
{
“component”: “Sugar crystals”,
“position”: “Separate layer”
},
{
“component”: “Small transparent threaded glass cup with weighted base (empty cup)”,
“position”: “Bottom”
}
],
“background”: “High-end dark background: Clean studio background, near-black graphite to charcoal gradient, soft and smooth”,
“lighting_and_style”: {
“lighting”: “Soft and controlled studio light, clear layered shadows beneath each component”,
“detail”: “Ultra-sharp macro realism, minimalist thin guide lines and English labels on the right”,
“category”: “High-end product infographic”,
“resolution”: “8K”
}
}
-------------
{
“subject”: “Hyper-realistic vertical exploded view infographic of a matcha milk cap fruit coffee drink”,
“layout”: “Center vertical alignment, components independently suspended with clear spacing”,
“layers”: [
{
“component”: “Fine matcha powder particles”,
“position”: “Top”
},
{
“component”: “Fresh strawberries and mango slices (with crystalline moisture)”,
“position”: “Separate layer”
},
{
“component”: “Thick savory cheese matcha milk cap layer (with delicate foam)”,
“position”: “Separate layer”
},
{
“component”: “Clear cold brew coffee liquid mixed with emerald matcha layer”,
“position”: “Separate layer”
},
{
“component”: “Crystal clear ice cubes and mint leaves”,
“position”: “Separate layer”
},
{
“component”: “Concentrated fruit syrup at the bottom (e.g., raspberry sauce)”,
“position”: “Separate layer”
},
{
“component”: “Minimalist straight striped glass cup (empty cup)”,
“position”: “Bottom”
}
],
“background”: “Fresh minimalist background: Bright studio environment, soft gradient from pale beige to light gray”,
“lighting_and_style”: {
“lighting”: “Bright natural light feel, with clear glass reflections and layered shadows”,
“detail”: “Ultra-sharp macro realism, minimalist thin guide lines and English labels on the right”,
“category”: “High-end product infographic”,
“resolution”: “8K”
}
}
---------------------
{
“subject”: “Hyper-realistic vertical exploded view infographic of a pink grapefruit peach smoothie”,
“layout”: “Center vertical alignment, components independently suspended with clear spacing”,
“layers”: [
{
“component”: “Dried rose petal fragments and gold sugar powder”,
“position”: “Top”
},
{
“component”: “Crystal clear grapefruit pulp particles”,
“position”: “Separate layer”
},
{
“component”: “Light cherry blossom pink whipped cream pile”,
“position”: “Separate layer”
},
{
“component”: “Silky peach oolong smoothie liquid layer (with delicate clinging texture)”,
“position”: “Separate layer”
},
{
“component”: “Fresh juicy peach chunks”,
“position”: “Separate layer”
},
{
“component”: “Chewy translucent amber pearls or tea jelly”,
“position”: “Separate layer”
},
{
“component”: “Minimalist exquisite tall-stemmed tulip glass (empty cup)”,
“position”: “Bottom”
}
],
“background”: “High-end Morandi pink background: Soft warm-toned cream pink to light beige gradient, pure and transparent”,
“lighting_and_style”: {
“lighting”: “Bright and fresh natural light, high-key illumination, light transparent shadows beneath each layer”,
“detail”: “Ultra-sharp macro realism, minimalist thin guide lines and English labels on the right”,
“category”: “High-end beverage visual poster”,
“resolution”: “8K”
}
}
Nano Banana Pro Community Hot Prompts Compilation
infographic-edu-visualA compilation of several high-engagement Nano Banana Pro prompts from the community, showcasing diverse applications like Pop Art product photography, origami sculpture rendering, anatomical illustration, and cinematic portraiture, emphasizing texture, lighting, and commercial realism.
展开提示词全文
Pop Art style plush beverage can product photography, highlighting Nano Banana Pro's commercial-grade rendering techniques for texture and color saturation Origami style portrait sculpture, Nano Banana Pro achieves precise color matching and hyper-realistic rendering of actual paper texture Country name food-filled layout illustration, Nano Banana Pro highlights the texture of traditional ingredients and artistic editing style applications Renaissance style anatomical study diagram, Nano Banana Pro generates detailed layering and Latin labels for educational illustration techniques Architectural heritage survey board design, Nano Banana Pro integrates technical drawings and photos for mixed-style display applications Lego landmark diorama, Nano Banana Pro prompt achieves cute 3D rendering and diverse architectural styles Cinematic portrait framing and dramatic lighting, Nano Banana Pro creates atmospheric depth and film grain effects High-end brand souvenir prompt details, Nano Banana Pro's creative technique for reconstructing everyday objects into luxury art pieces Cosmetic spray product photography, Nano Banana Pro emphasizes realistic materials and botanical elements for e-commerce style applications Celebrity plush toy design, Nano Banana Pro achieves friendly cartoon textures and fun scene arrangement applications Multi-module style illustration fusion, Nano Banana Pro's transformation technique and vibrant expression from cartoon to anime Chocolate coffee exploded infographic, Nano Banana Pro highlights layered textures and high-end lifestyle style AI makeup replication guide, Nano Banana Pro analyzes and applies fine makeup details for instructional prompt techniques Pop art theme rendering, Nano Banana Pro uses a limited color palette to create dynamic and eye-catching composition styles Tsundere expression reality editing, Nano Banana Pro uses narrative anchors to achieve emotional intensity and identity locking applications Cartoon and reality split portrait, Nano Banana Pro's mixed-style technique for seamless transition of texture and detail Color illustration style matrix, Nano Banana Pro's modular library for generating multiple animated variations from photos Coffee ingredient dynamic exploded view, Nano Banana Pro combines motion prompts to achieve smooth separation and realistic texture High-end brand souvenir reconstruction, Nano Banana Pro's surprising design style with diverse categories and luxurious materials Celestial dream theme portrait, Nano Banana Pro's surreal technique with glowing edges and a dreamy color palette
Conceptual Object Feasibility Image Prompt
infographic-edu-visualA simple, direct prompt designed to test the feasibility of an object's construction by asking the AI to generate an image that visually explains the solution to the problem. This is useful for conceptual design and engineering visualization.
展开提示词全文
"Could this object be built? Make an image showing how to answer this problem."
Psychedelic Mathematics Fractal Prompt for Menger Sponge
infographic-edu-visualA complex, multi-part instruction prompt designed to visualize the mathematics of a fractal set, specifically the Menger sponge. The prompt sets the scene on an 1980s drafting table where the fractal equation's ink spirals into a 3D geometric rendering, illuminated by neon computer monitor glow.
展开提示词全文
<instruction> Role: Act as a Mathematician and Architect. Input:[fractal set]. Analysis: The fractal set, infinite recursion, coastlines, ferns, every aspect Goal: A drafting table where the math spirals into infinity. Rules: Base: Graph paper and heavy computers from the 1980s. Transformation: The equation for the fractal is written on the page. The ink from the equation is spiraling up into a 3D fractal set relevant to the input. Scale: Macro shot, implying infinite detail. Details: The tip of the pen is touching the paper, and the ink flow is already branching infinitely. Lighting: Neon computer monitor glow reflecting off the glossy ink. Output: Psychedelic mathematics, sharp geometric rendering. </instruction>
3D Pixar-Style Hook Image: Programmable Money to Intelligence
infographic-edu-visualA prompt for generating a 3D Pixar-style hook image illustrating the transition from 'OLD DEFI' (rusty pipes) to 'programmable intelligence' (glowing, crystalline conduit). It features a fire character in a VR headset pointing at the transformation, with specific instructions for composition, depth of field, and neon green accent lighting.
展开提示词全文
3D Pixar-style hook image, 16:9 format. CHARACTER: Fire character in VR headset with OpenGradient logo. Expression: realizing/pointing. Pose: standing in a construction site, pointing at a transformation in the pipes. SCENE: A messy wall of rusty, leaking pipes labeled "OLD DEFI". One section of the pipe transforms into a glowing, crystalline, see-through conduit pulsating with green "brain" energy. FOREGROUND: A heavy wrench and blurred blueprints on a workbench in the corner. Creates depth. BACKGROUND: Dark industrial background but lit up by the green glow of the new pipe. TEXT: "PIPING TO BRAINS" on LEFT, bold white with glow. COMPOSITION: Text dominant 70/30. Depth of field: blurred foreground -> sharp subject -> slight background blur. Cinematic lighting with neon green accent.
Food History Diorama in Mandala Format (Spicy Chicken Wings)
infographic-edu-visualA complex, multi-layered prompt for generating a hyper-realistic 'Food History Diorama' arranged in a Mandala format, using spicy chicken wings as the subject. It requires five concentric rings, each representing a different historical era (Modern, Commercial, Domestic, Industrial, Ancient), populated by tiny 1:87 scale chef figures dressed appropriately for that era, with specific instructions for lighting, scale, and texture changes across the rings.
展开提示词全文
Input Variable: {argument name="food item" default="Spicy Chicken Wings"}
System Instruction:
Generate a hyper-realistic, high-angle "Food History Diorama" arranged in a Mandala format.
CRITICAL: The scene must be populated by Tiny 1:87 Scale Figures (Chefs) that correspond to the specific era of each ring.
1. Timeline Analysis:
Analyze the history of the Input Food to determine the Attire and Tools of the workers in 5 eras:
Stage 0 (Center): The Modern Chef (White Coat, Toque, Tweezers).
Stage 1 (Commercial): The Fast Food Worker (Visor, Polo Shirt, Headset).
Stage 2 (Domestic): The Home Cook (Floral Apron, Oven Mitts).
Stage 3 (Industrial): The Butcher/Baker (Dirty White Apron, Cleaver, Rolled Sleeves).
Stage 4 (Ancient): The Hunter/Gatherer (Tunic, Loincloth, Stone Tools, Fire).
2. The Composition :
Perspective: High Angle (75 Degrees). Not completely flat. We need to see the bodies of the tiny figures, not just their heads.
The Orbits: 5 Distinct Concentric Rings.
The Boundary (The Catwalk): Between each ring, there is a visible Negative Space (a thin gap). This is where the tiny chefs stand, presenting the food to the viewer.
3. The Rings & The Residents Logic):
The Center (Modern Pinnacle):
Food: Deconstructed, gourmet plating on slate.
The Figure: A Master Chef carefully placing a micro-green garnish with tweezers.
Ring 1 (The Commercial Age):
Food: Bright packaging, uniformity.
The Figure: A Teenage Fast Food Worker holding a tray or a soda cup, standing next to the cardboard boxes.
Ring 2 (The Domestic Age):
Food: Casserole dishes or patterned china.
The Figure: A 1950s Housewife or Home Cook holding a serving spoon or pie cutter.
Ring 3 (The Industrial Age):
Food: Cast iron skillets, tin plates, hearty portions.
The Figure: A burly 19th Century Butcher or Cook holding a heavy knife or iron ladle.
Ring 4 (The Ancient Origin):
Food: Cooking over open fire, stone tools, raw ingredients (but cooked/charred enough to look appetizing).
The Figure: An Ancient Human tending to a mini-campfire or grinding spices with a stone.
4. The Background Morph:
The surface texture underneath the figures changes with them:
Center: Polished Stone.
Middle: Linoleum/Wood Table.
Edge: Dirt/Earth.
5. Lighting & Scale:
Tilt-Shift: Blur the outer edges slightly to emphasize the miniature scale of the people.
Shadows: The figures must cast long shadows across the food to prove they are physically standing there.
Output: ONE image, 1:1 Aspect Ratio, 8k Resolution, Miniature Photography style.
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。