← 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 577 条

Exploded View Product Photography Prompt

ecommerce-main-image

A prompt for generating high-end product advertising imagery featuring an exploded view of a product. It emphasizes revealing inner mechanics, micro-details, perfect alignment, and uses macro photography technical specifications (100mm lens, f/8, 8k) against a clean white background.

展开提示词全文
[{argument name="product name" default="product"}], high-end product advertising, white seamless background, exploded view with inner mechanics revealed, outer shell hovering above core, micro screws and components suspended, perfect alignment guides implied, crisp soft shadow, ultra realistic, macro product photography, 100mm lens look, f/8, 8k, 1:1

Character Ekiben (Lunch Box) Product Shot

ecommerce-main-image

A highly detailed prompt for Nano Banana Pro to generate a photorealistic product shot of a 'Character Ekiben' (character-themed lunch box), emphasizing commercial packaging design, food realism, specific composition (flat lay), and the use of food items to represent the character's features.

展开提示词全文
Character Name: {argument name="キャラクター名" default="[Character Name]"}
(Scene/Moment)
A single shot capturing the moment the lid of a character-themed lunch box (Ekiben style), packaged for sale, is opened.

The transparent or paper lid is partially covering the lunch box, revealing the contents.

(Packaging/Lid Expression)
The outside of the lid is printed with a commercial package design based on the character in the reference image. Various exaggerated sales phrases based on the reference image are displayed with high quality and high sense.

Design that looks like it would be lined up in an actual Ekiben stall.
Illustration of the character deformed with a 'food' theme.
Limited color palette, layout resembling food labels, logos, and catchphrases.
Display a price that greatly reflects the concept of the reference image and the lunch box.

Includes a humorous product name that utilizes the character's personality.
If a character name is set at the beginning, use it.
Realistic depiction of print gloss, paper thickness, and folded parts.
*This lid is strongly linked to the concept of the contents.
(Composition/Shooting Style)
Shoot the lunch box placed on a table from a **slightly diagonal top-down perspective (product photography flat lay)**.

8K resolution, ultra-realistic food photography.

Quality that would not look out of place in a convenience store, department store basement, or Ekiben fair.
(Container - Lunch Box)
A mass-produced, realistic lunch box container.

Common lunch box containers such as black, white, or wood grain.
With dividers or integrated.
Realistic depiction of rounded corners, molding marks, and shadows on the rim.

Basic Structure of Character Representation
Face/Body:

Three-dimensionally shaped rice (white rice/seasoned rice/mixed rice, etc., changing according to the concept).
Expression/Outline:

Three-dimensionally expressed using nori (seaweed), salted kelp, sesame seeds, fried pasta, chopped vegetables, etc.
Concept-Specific Side Dishes
The concept exaggerates the characteristics of the reference image.
Not a fixed menu, but changes freely according to the character and world view.
All side dishes are composed only of real ingredients and cooking methods,

Each one has a solid three-dimensional feel and texture.
(Color Design)
Do not use the colors of the reference image directly,
Translate using only natural colors as food ingredients.
White/light brown of rice.
Golden brown of fried food.
Green of vegetables.
Red of tomato/plum/carrot.
Yellow of egg.
Black of nori/sesame.
Designed to recognize the character not by 'color coding' but by
Differences in texture, shape, and arrangement.
(Text/Logo Expression: Reinforcing the feeling of a product for sale)
Three-dimensional expression of the product name and catchphrase using food items in the empty space within the lunch box.

Exaggerate the characteristics of the reference image.
The text is composed entirely of “edible items.”
(Background/Environment)
Randomly select an outdoor setting.
Natural light from the side.
Emphasize the shine of oil on fried chicken, the moisture of the rice, and the freshness of the vegetables.
The overall color temperature is warm, with light that makes it look the most delicious at the point of sale.
(Overall Tone)
“Cute” + “Looks like it could actually be sold.”
Fusion of Character Bento × Product Photography × Food Sizzle.

Master Prompt for Premium Minimalist Product Photography

ecommerce-main-image

A reusable master prompt template designed for generating premium, minimalist product photography (UGC statics). It guides the user to specify the brand, product, surface, and relevant props, ensuring clean, high-clarity results with soft diffused lighting, subtle rim light, and realistic textures suitable for luxury advertising.

展开提示词全文
Premium minimalist product photography. A {argument name="brand name" default="BRAND"} {argument name="product name" default="PRODUCT"} featuring {argument name="packaging details" default="PACKAGING/LOGO DETAILS"} placed at the center of the frame. The product rests on {argument name="surface type" default="SURFACE"} surrounded by {argument name="relevant props" default="RELEVANT PROPS"}. Clean matte {argument name="background color" default="COLOR"} background with subtle gradient. Soft diffused lighting with gentle rim light creates a luminous glow highlighting {argument name="key features" default="KEY FEATURES"}. Sharp focus, high clarity, realistic textures, luxury advertising style, modern branding, ultra-realistic, 8K detail, high dynamic range. 

Negative Prompt: hands, people, faces, clutter, harsh reflections, label distortion, unreadable text, warped product, hard shadows, grain, noise, low resolution, CGI look, cartoon style, messy spills, uneven lighting, watermark

Commercial Fashion Photograph with Strict Garment Preservation (Variant)

ecommerce-main-image

A structured JSON prompt, highly similar to another entry, for generating a high-end commercial lifestyle photograph. It strictly requires preserving the exact details of a garment from a reference image, featuring a white American female model in a natural, confident pose on an outdoor urban sidewalk setting with soft natural daylight.

展开提示词全文
{
  "task_configuration": {
    "type": "GENERATE",
    "sub_type": "commercial_lifestyle_photograph",
    "reference_logic": "STRICT_GARMENT_PRESERVATION_FROM_INPUT",
    "aesthetic": "high_end_fashion_campaign",
    "output_quality": "high_resolution_photorealistic"
  },
  "subject_definition": {
    "identity": {
      "demographic": "white American female model",
      "physique": "fit",
      "appearance": "beautiful, naturally styled"
    },
    "skin_and_features": {
      "realism_rule": "macro_level_human_realism; NO artificial smoothing or filtering",
      "texture_details": [
        "visible natural pores",
        "light blemishes and imperfections",
        "soft expression lines around eyes/mouth",
        "light freckles across nose/cheeks",
        "natural skin highlights and subsurface scattering"
      ],
      "makeup": "minimal, natural or bare skin look"
    },
    "attire_constraints": {
      "source": "garment_from_input_reference_image",
      "preservation_rules": [
        "exact color dye and pattern",
        "exact fabric weave and texture",
        "exact thread stitching details",
        "exact fit, drape, and silhouette on the body"
      ],
      "modification_permission": "NONE"
    },
    "pose": {
      "framing": "full_body_standing",
      "style": "natural, relaxed, confident",
      "orientation": "facing camera to showcase garment front"
    }
  },
  "environment_definition": {
    "location_type": "outdoor_urban_sidewalk",
    "specific_context": "outside a stylish cafe or artisan building facade",
    "contextual_logic": "architecture and decor must visually complement the style of the reference clothing",
    "atmosphere": "elevated, authentic city life, cinematic quality",
    "background_elements": [
      "textured building materials (brick, stone, wood)",
      "cafe seating or planter boxes",
      "pavement textures"
    ]
  },
  "composition_and_layout": {
    "camera_principles": [
      "commercial fashion standards",
      "golden ratio alignment of subject",
      "product-centered focus",
      "grid alignment"
    ],
    "framing_scale": "wide full shot (head to toe)",
    "spatial_margins": {
      "top_margin": "generous clear space above head for potential typography/cropping",
      "side_margins": "balanced clear space",
      "bottom_margin": "clear space below feet"
    }
  },
  "lighting_and_optics": {
    "source": "natural daylight",
    "quality": "soft, diffused sunlight or open shade",
    "color_temperature": "warm undertones",
    "shadows": "clean, natural falloff defining form without harshness"
  },
  "constraints_and_prohibitions": {
    "must_not_render": [
      "airbrushed skin",
      "plastic textures",
      "studio backdrop",
      "altered clothing design",
      "overly posed look"
    ]
  }
}

Commercial Fashion Photograph with Strict Garment Preservation

ecommerce-main-image

A structured JSON prompt for generating a high-end commercial lifestyle photograph. The core instruction is to strictly preserve the exact details (color, pattern, texture, fit) of a garment from a reference image, placing the subject (a white American female model) in a natural, relaxed pose on an outdoor urban sidewalk setting with soft natural daylight.

展开提示词全文
{
  "task_configuration": {
    "type": "GENERATE",
    "sub_type": "commercial_lifestyle_photograph",
    "reference_logic": "STRICT_GARMENT_PRESERVATION_FROM_INPUT",
    "aesthetic": "high_end_fashion_campaign",
    "output_quality": "high_resolution_photorealistic"
  },
  "subject_definition": {
    "identity": {
      "demographic": "white American female",
      "physique": "fit",
      "appearance": "beautiful, naturally styled"
    },
    "skin_and_features": {
      "realism_rule": "macro_level_human_realism; NO artificial smoothing or filtering",
      "texture_details": [
        "visible natural pores",
        "light blemishes and imperfections",
        "soft expression lines",
        "light freckles across nose/cheeks",
        "natural skin highlights"
      ],
      "makeup": "minimal, natural or bare skin look"
    },
    "attire_constraints": {
      "source": "garment_from_input_reference_image",
      "preservation_rules": [
        "exact color dye and pattern",
        "exact fabric weave and texture",
        "exact thread stitching details",
        "exact fit, drape, and silhouette on the body"
      ],
      "modification_permission": "NONE"
    },
    "pose": {
      "framing": "full_body_standing",
      "style": "natural, relaxed, confident",
      "orientation": "facing camera to showcase garment"
    }
  },
  "environment_definition": {
    "location_type": "outdoor_urban_sidewalk",
    "specific_context": "outside a stylish cafe or boutique building facade",
    "contextual_logic": "architecture and decor must visually complement the style of the reference clothing",
    "atmosphere": "elevated, bustling but serene city life",
    "background_elements": [
      "textured building materials (brick, stone, wood)",
      "cafe seating or plants",
      "pavement textures"
    ]
  },
  "composition_and_layout": {
    "camera_principles": [
      "commercial fashion standards",
      "golden ratio alignment of subject",
      "product-centered focus"
    ],
    "framing_scale": "wide full shot",
    "spatial_margins": {
      "top_margin": "generous clear space above head for potential typography/cropping",
      "side_margins": "balanced clear space",
      "bottom_margin": "clear space below feet"
    }
  },
  "lighting_and_optics": {
    "source": "natural daylight",
    "quality": "soft, diffused sunlight or open shade",
    "color_temperature": "warm undertones",
    "shadows": "clean, natural falloff defining form"
  },
  "constraints_and_prohibitions": {
    "must_not_render": [
      "airbrushed skin",
      "plastic textures",
      "studio backdrop",
      "altered clothing design",
      "overly posed look"
    ]
  }
}

Solarpunk Product Showcase with Bioluminescence

ecommerce-main-image

A detailed prompt for generating a photorealistic solarpunk product showcase. It describes an elegant grid arrangement of sustainable technology products with organic curves, living moss, and bioluminescent glow, set against a verdant living wall background. The scene is lit by golden hour sunlight, aiming for a high-end commercial photography aesthetic that blends Korean minimalist design with natural elements.

展开提示词全文
A stunning solarpunk product showcase featuring an elegant grid arrangement of sustainable technology products seamlessly integrated with lush botanical elements. The scene displays bio-engineered devices with flowing organic curves and living moss accents arranged in perfect symmetry on a reclaimed wood surface. Each product emanates a soft bioluminescent glow, featuring translucent bio-plastic casings with visible internal plant root systems and flowing water channels. The background reveals a verdant living wall cascade with hanging air-purifying vines, integrated solar panel leaves, and delicate flowering pods that power the displayed technology.

Golden hour sunlight streams through floor-to-ceiling windows, casting warm amber rays that dance across the green foliage and illuminate the products with a dreamy, ethereal backlight. Soft volumetric lighting creates gentle lens flares and highlights the organic textures of both nature and technology. The atmosphere feels optimistic and serene, embodying a harmonious future where innovation and nature coexist beautifully.

Shot from a slightly elevated three-quarter angle using a wide-angle lens with shallow depth of field, creating artistic bokeh in the background vegetation while keeping the product grid in sharp focus. The composition follows rule of thirds with leading lines created by the wooden planks and vine arrangements. Professional commercial photography style with vibrant color grading emphasizing rich emerald greens, warm golden tones, and creamy white highlights. The aesthetic balances minimalist {argument name="design style" default="Korean"} design sensibilities with abundant natural elements, creating an Instagram-worthy visual that suggests premium eco-luxury and sustainable innovation. Photorealistic rendering with high dynamic range, crisp details, and subtle film grain for organic authenticity.
A stylish handwritten signature Willy is elegantly and small letters placed at the Bottom Right corner.

Winter Cabin Scene with Frosted Window and Coca-Cola Can

ecommerce-main-image

A prompt for generating an ultra-realistic winter scene viewed from indoors through a frosted window. The focus is on a Coca-Cola can placed on the sill, emphasizing condensation and frost details. The background shows a cozy, snowy log cabin with warm interior lights, utilizing cinematic depth of field and soft bokeh.

展开提示词全文
Ultra-realistic winter cabin scene viewed from indoors through a frosted window. A cold {argument name="product" default="Coca-Cola can"} placed on the wooden window sill, condensation and frost crystals visible on the glass. Outside, heavy snowfall, snow-covered pine trees, and a cozy wooden log cabin with warm orange lights glowing from the window. Soft firelight flickering near the cabin, cinematic depth of field, shallow focus on the Coca-Cola can, background slightly blurred. Moody winter atmosphere, contrast between warm interior tones and cold blue snowy exterior. Photorealistic lighting, soft bokeh snow particles, premium commercial photography style, ultra-detailed textures, 8K resolution.
Negative Prompt (optional):
cartoon, illustration, low quality, blurry, overexposed, distorted logo, extra text, watermark, unrealistic proportions

Ultra-Realistic Artisan Chocolate Product Visuals

ecommerce-main-image

A highly complex, multi-image prompt structure for generating ultra-realistic food photography of artisan chocolates. It details four distinct compositions (praline tower, ruby chocolate tablet, white chocolate bonbons, dark chocolate bar), specifying fillings, lighting, textures, and background for a luxury editorial aesthetic.

展开提示词全文
"style": "ultra-realistic food photography, luxury editorial, macro-detail, natural textures",
  "images": [
    {
      "id": "image_1",
      "subject": "assorted praline tower",
      "composition": "staggered vertical tower, center frame, loose organic stacking",
      "details": {
        "fillings": [
          "hazelnut chunks irregularly clumped at base",
          "raspberry gel naturally puddled",
          "salted caramel with realistic flow lines",
          "coffee ganache with smooth wave texture",
          "passionfruit filling with visible pulp specks"
        ],
        "accent": "one unique metallic gold nut per filling type placed at layer transitions",
        "stand": "brushed gold stand with subtle reflections"
      },
      "lighting": {
        "type": "dramatic side lighting",
        "angle": "35 degrees left",
        "effects": "authentic filling refractions, layered shadow play"
      },
      "background": "{argument name="background color 1" default="teal-to-navy"} gradient with suspended gold motes",
      "mood": "luxurious, indulgent, artisanal depth"
    },
    {
      "id": "image_2",
      "subject": "ruby chocolate tablet",
      "composition": "floating hexagonal segments above black textured paper liner",
      "details": {
        "surface": "hand-tempered imperfections, translucent ruby pink",
        "inclusions": "embedded fruit flecks visible through chocolate",
        "motion": "ruby cacao nibs falling in gravity-realistic arc from one segment"
      },
      "lighting": {
        "key": "top-down at 12 o'clock",
        "rim": "soft pink rim light at 3 o'clock",
        "effects": "authentic shadows, enhanced translucency"
      },
      "background": "black-to-warm pink radial gradient with subtle sparkle specks",
      "mood": "modern, vibrant, floating tension"
    },
    {
      "id": "image_3",
      "subject": "white chocolate bonbons",
      "composition": "organic cluster on clear glass stand",
      "details": {
        "marbling": [
          "central bonbon with irregular orange passionfruit veins",
          "surrounding bonbons with pink raspberry swirls",
          "green matcha flecks with varied density"
        ],
        "cutaway": "one bonbon sliced vertically showing gel core with real fruit speckles",
        "props": "dried fruit flecks scattered below (orange zest curls, raspberry seeds)"
      },
      "lighting": {
        "key": "soft high-key front light at 10 degrees",
        "rim": "rear rim light at 35 degrees",
        "effects": "enhanced marbling contrast and glass refractions"
      },
      "background": "soft taupe with fruit-toned bokeh",
      "mood": "elegant, fresh, handcrafted"
    },
    {
      "id": "image_5",
      "subject": "dark chocolate pistachio bar",
      "composition": "vertical bar centered on polished black granite slab",
      "details": {
        "cross_section": "precision side cut revealing layered pista

Gilded Delftware Product Signature Prompt

ecommerce-main-image

A short, descriptive prompt aiming to generate a signature product image in the style of Gilded Delftware, likely for a brand presentation.

展开提示词全文
Signature brand product to Gilded Delftware

Stone-Carved Statue Prompt for Nano Banana Pro

ecommerce-main-image

A concise prompt for Nano Banana Pro to generate a cinematic, photorealistic image of a tiny stone-carved statue of a specified person, sitting on a sculptor's workbench with dust and directional warm light emphasizing texture.

展开提示词全文
A tiny stone-carved statue of {argument name="name" default="[NAME]"}, with chisel marks and uneven surfaces, sitting on a sculptor’s workbench. Stone dust, small chisels, and directional warm light emphasizing texture and form. Cinematic realism. 1080×1080.

Miniature Figurine Prompt for Nano Banana Pro

ecommerce-main-image

A prompt in Chinese and English for Nano Banana Pro to create a miniature, full-body, isometric, realistic figurine of a person based on an uploaded photo, allowing customization of clothing, profession, and action.

展开提示词全文
Make a miniature, full-body, isometric, realistic figurine of this person, wearing {argument name="clothing" default="ABC"}, doing {argument name="action" default="XYZ"}, on a white background, minimal, 4K resolution

Fashion Catalog Item Extraction from Reference Image

ecommerce-main-image

A detailed system prompt for a professional fashion catalog creator AI. It instructs the model to analyze the clothing worn by a man in a reference image and strictly extract the items into four categories (Outerwear, Shirt/Innerwear, Pants, Shoes). The output must be a clean, high-quality product photograph on a white background, displaying only the extracted items with Japanese labels, without redesigning or showing the human body.

展开提示词全文
You are a professional fashion catalog creator.
Analyze the clothing worn by the man in the reference image.
Based strictly on the actual designs of the clothes he is wearing, extract and separate them into the following four categories:

① Outerwear / jacket / coat
② Shirt / innerwear / dress shirt
③ Pants / slacks / denim
④ Shoes / sneakers / leather shoes

Each extracted item must accurately reflect the original clothing’s color, material texture, shape, and details.
Do NOT redesign, modify, stylize, or reinterpret the clothing in any way.
Do NOT show the human body. Extract and display the clothing items only.
The output image must be:
・white background
・front-facing view
・no shadows, no noise
・high-quality product photography, apparel e-commerce style
Arrange the four items neatly in either a horizontal row or a 2×2 grid.
Add Japanese labels to each item exactly as follows:

① Outerwear / jacket / coat, etc.
② Shirt / innerwear / dress shirt, etc.
③ Pants / slacks / denim, etc.
④ Shoes / sneakers / leather shoes, etc.

Create a clean, easy-to-read catalog-style image.
ultra high resolution, photorealistic, studio product lighting, flat lighting, extremely detailed fabric texture, apparel catalog quality

Negative prompt:
anime, illustration, cartoon, stylized, redesigned clothing, fashion sketch, mannequin, human body, model wearing clothes, background, shadow, reflection, blur, low quality, noisy image, dramatic lighting

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。