← 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

Luxury Watch Product Photography Prompt: Luxury vs. Absurdity

ecommerce-main-image

A structured prompt for generating product photography in an advertising world context, focusing on a luxury watch. The prompt uses 'core tension' (Luxury vs. Absurdity) and 'twist mechanisms' (functional mismatch, material displacement, shape mutation) to create a visually striking and humorous image, set on polished black acrylic with strong backlighting.

展开提示词全文
{
  "_world": "advertising",
  "creation_intent": "Entertainment or Joke",
  "generation_logic": "Person or character-centric",
  "subject_kit": {
    "primary_subject": "{argument name="primary subject" default="Luxury Watch"}",
    "secondary_elements": [
      "Velvet Cushion",
      "Certification Document"
    ]
  },
  "core_tension": "Luxury vs. Absurdity",
  "twist_mechanisms": [
    "Functional Mismatch",
    "Material Displacement",
    "Shape Mutation"
  ],
  "stage_context": "Polished Black Acrylic",
  "composition_rule": "Tight Crop Extreme Close-up",
  "lighting_rule": "Backlight with Lens Flare",
  "imaging_assumption": "Warm-toned Desktop Perspective",
  "deliverable_type": "Main Advertising Visual",
  "creative_directive": null,
  "oblique_strategy": null,
  "_evaluation": {
    "verdict": "PASS",
    "violations": [],
    "warnings": []
  }
}

Editorial Product Photography Prompt for Levitation Effect

ecommerce-main-image

A detailed image generation prompt designed for creating editorial-style product photography featuring a levitation effect. It specifies cinematic lighting, soft shadows, motion blur on trailing elements, and an editorial fashion-magazine framing to achieve a suspended, high-end look.

展开提示词全文
{argument name="product" default="[PRODUCT]"} and supporting props floating in mid-air, soft shadows anchored below, motion blur on trailing elements, suspended-from-the-moment storytelling, cinematic three-point lighting, editorial fashion-magazine framing.

Branded Fast Food Leather Bag

ecommerce-main-image

A simple prompt requesting the generation of a branded fast food leather bag.

展开提示词全文
Branded fast food leather bag

Cosmic Product Photography: Futuristic Energy Serum

ecommerce-main-image

A detailed prompt for generating high-end, hyper-realistic product photography of a fictional bio-tech serum called 'PulseCharge Serum.' The prompt specifies intricate details about the bottle design (concentric alloy rings, frosted glass), the liquid (cobalt-red with micro-structures), technical typography, and the lighting setup (clean, high-contrast, 100mm macro lens) to achieve an electric, futuristic mood.

展开提示词全文
High-end cosmic premium product photography of a futuristic energy-balancing serum titled “{argument name="product name" default="PulseCharge Serum"}”, visualized as an advanced bio-tech concept launch.

BOTTLE DESIGN:
Tall, streamlined bottle with concentric alloy rings appearing magnetically aligned around the body. Frosted high-density glass with carbon-pattern polymer grip bands.

LIQUID:
Intense cobalt-red liquid with crystalline micro-structures suspended within, representing kinetic energy and bioelectric activation.

TYPOGRAPHY (PRINTED ON BOTTLE):
Matte white ink, technical precision typography:
- ELECTRO BALANCE SYSTEM
- CODE: PC-61
- OUTPUT: 980J

BACKGROUND:
Soft steel-blue pastel background, minimal and cool-toned, complementing the vivid red liquid.

LIGHTING:
Clean high-contrast lighting with sharp electric reflections on metal surfaces. Luminous liquid core with controlled highlights.

PHOTOGRAPHY:
100mm macro lens, 8K resolution, hyper-realistic detail, razor-sharp textures, shallow depth of field.

OVERLAYS:
Bottom Left:
“PulseCharge Serum – Engineered to support alertness, balance, and sustained internal energy.”

Bottom Right:
Minimal lightning-line logomark in dark neutral gray.

MOOD:
Electric, engineered, futuristic, precision-driven.

NEGATIVE PROMPTS:
No clutter, no people, no lens flares, no cyberpunk exaggeration, no noise, no text distortion.

Multilingual Figure Product Introduction Layout Prompt for Nano Banana Pro

ecommerce-main-image

A detailed, structured prompt designed to transform a reference image of a character into a photorealistic PVC figure product introduction layout, complete with product information, logos, and close-up views. The prompt supports Japanese, English, German, and French text generation for the product details and requires a reference image of the character.

展开提示词全文
language: "{argument name="display language" default="ja"}"
# Supported values:
# - ja : Japanese
# - en : English
# - de : German
# - fr : French
# The selected language determines all displayed product text.

product_name: "{argument name="product name" default="ARBITRARY_PRODUCT_NAME"}"
manufacturer_name: "{argument name="manufacturer name" default="ARBITRARY_MANUFACTURER_NAME"}"

subject: >
  The character from reference image A, faithfully preserved in design, proportions,
  facial features, hairstyle, outfit details, and color palette.
  The character is transformed into a highly detailed, photorealistic PVC figure.
  Sculpting style and overall aesthetic is inferred directly from the reference image.
  The figure is presented as a 1/7 scale collectible.

composition: >
  Product introduction layout inferred based on the selected language.
  Vertical composition with a 3:4 aspect ratio.
  A large main visual of the full figure.
  A single, clearly defined product information area containing all textual elements.
  Product name logo and manufacturer name logo are each displayed exactly once.
  Multiple inset close-up panels are included.
  Each inset focuses on a different physical area or feature of the figure.
  No two inset panels depict the same part or the same visual characteristic.
  Inset panels must be visually and conceptually distinct.

action: >
  Static collectible figure pose with no movement.
  Emphasis on sculpt accuracy, proportions, and surface detail.

location: >
  Neutral studio-like environment inferred for product photography.
  Minimal, non-distracting background.

style: >
  Photorealistic product rendering and photography style.
  Artistic tone and mood inferred entirely from the reference image.

camera_lighting: >
  Camera angle and lighting optimized for collectible figure presentation.
  Realistic studio lighting interacting with PVC surfaces.
  Glossy highlights on hair and cl

Cozy Indoor Fashion Shot Prompt (Gray Turtleneck Set)

ecommerce-main-image

A prompt for generating a high-quality, full-body indoor fashion photograph of a model wearing a specific gray oversized turtleneck and wide-leg trousers. It requires maintaining the exact fabric texture and color from a reference image, set in a cozy, warm, modern bedroom environment.

展开提示词全文
{
  "description": "A full-body image of a different female American model wearing the exact same outfit as in the reference: a soft gray oversized turtleneck sweater made of wool or cashmere, with ribbed cuffs, collar, and hem, paired with matching gray wide-leg trousers. The model should stand in a relaxed, natural pose with a gentle, welcoming smile and confident yet calm posture. Her hair should be styled simply — shoulder-length or slightly wavy — and she should appear approachable and cozy. The sweater’s color, texture, and proportions must remain completely identical to the reference image.",
  
  "style": "High-quality indoor fashion photograph in a cozy, warm, realistic bedroom setting. The focus should be on comfort, softness, and casual elegance. The atmosphere should feel natural, modern, and homely.",
  
  "lighting": "Soft, diffused indoor lighting around 3000–3200K, coming from bedside lamps or ceiling lights. There should be no sunlight or window glare. Maintain smooth illumination across the outfit, highlighting the sweater’s soft wool texture and natural folds. Lighting should be warm, gentle, and cozy — no harsh shadows or bright reflections.",
  
  "camera": "Full-body shot at eye level, maintaining a natural and flattering angle. The model should be standing comfortably or leaning slightly near a bed or dresser, with a relaxed composition that highlights the outfit from head to toe. Depth of field should be slightly shallow to softly blur the background while keeping the model sharp.",
  
  "focus": "Keep the gray turtleneck sweater and trousers exactly as in the reference — same knit texture, ribbed cuffs, and slightly oversized fit. Ensure the wool appears realistic and soft. Preserve the monochrome color scheme and natural draping of the outfit.",
  
  "environment": "A modern, cozy bedroom with warm neutral tones — beige or cream walls, a neatly made bed with soft bedding, wooden or carpet flooring, a side lamp, and indoor plants. The space should feel calm, elegant, and inviting, with only indoor light sources visible. No sunlight or window brightness should appear in the frame.",
  
  "negative_prompt": [
    "different sweater color or texture",
    "tight or fitted outfit",
    "outdoor or studio background",
    "sunlight or window glare",
    "cropped or half-body shot",
    "harsh shadows or overexposed lighting",
    "different outfit type",
    "glossy or synthetic fabric"
  ]
}

E-commerce Full-Body Product Shot Prompt (Olive Green Dress)

ecommerce-main-image

A prompt for generating a clean, editorial-grade full-body e-commerce image of a model wearing a specific olive green short dress. It emphasizes maintaining the exact fit and fabric texture from a reference image, ensuring the model and dress are fully visible against a minimalist beige background.

展开提示词全文
{
  "description": "Full-body photo of the same female model wearing the exact same olive green short dress as in the reference — identical fit, fabric texture, color, neckline, sleeve shape, and length ending above the knees. The model must be fully visible from head to toe within the frame, including both feet and space above the head. The background is a clean light beige tone with soft shadows, maintaining a minimalist and premium look.",
  
  "appearance": "The model appears elegant and confident, with natural makeup and softly styled straight hair. Her facial expression should be calm, relaxed, and professional. Skin should look natural with subtle texture — no airbrushing.",
  
  "pose": "Full-body standing pose with relaxed posture. The model faces slightly toward the camera, one leg slightly ahead of the other for balance. Hands rest naturally at sides or lightly on hips, ensuring the dress remains fully visible. Both feet must be in frame.",
  
  "lighting": "Soft, evenly diffused lighting in a neutral warm tone (around 3800K–4000K). No sunlight or harsh studio reflections. Maintain realistic skin tone and true fabric color.",
  
  "environment": "Simple beige background, smooth gradient with no props or distractions. The focus remains entirely on the model and dress.",
  
  "camera": "Full-body vertical composition, framed slightly wider than before to include the full model from head to toe with extra space above and below. Eye-level perspective with sharp focus on model and dress, slightly soft background for depth.",
  
  "style": "Photorealistic, editorial-grade fashion image with clean lines, elegant tone, and refined simplicity — perfect for e-commerce or lookbook display.",
  
  "focus": "Ensure the entire model, including feet, is clearly visible. Maintain accurate proportions and fabric realism. The hemline must be short (above the knees) and not extended.",
  
  "negative_prompt": [
    "cropped frame (head or feet missing)",
    "long or maxi dress",
    "props or cluttered background",
    "bright studio light or sunlight",
    "overexposed lighting",
    "AI-smooth skin",
    "tilted camera angle"
  ]
}

Composite Product Photography Prompt (Etsy Style)

ecommerce-main-image

A versatile prompt designed for generating composite product photography shots suitable for e-commerce (like Etsy). It specifies arranging a hero shot, ambient lifestyle frame, and close-up texture detail in a cohesive layout, emphasizing warm, cozy home settings, natural lighting, and handcrafted textures.

展开提示词全文
Lifestyle product photography of {argument name="product" default="ceramic mug"} styled in a warm, cozy home setting. Hero shot + ambient lifestyle frame + close-up texture detail arranged in a cohesive storytelling layout. Natural window lighting, soft shadows, handcrafted textures, warm earthy tones, inviting Etsy-style ambience with a cinematic softness.

Artisan Toy Product Photography Prompt

ecommerce-main-image

A highly detailed product photography prompt for generating an image of a fictional artisan toy, the 'Kál-Húf Lantern.' It specifies materials (dark Nordic spruce, bioluminescent moss), complex PBR layering, macro lens camera settings, and a dual-lighting setup (harsh flash and internal glow) to create a fusion of Frutiger Aero and Dreamcore aesthetics.

展开提示词全文
Subject: A high-end artisan toy, the "{argument name="toy name" default="Kál-Húf Lantern"}," a 15cm spherical object crafted from dark, polished Nordic spruce wood. The sphere features intricate, laser-etched Kúlon Séli runes that glow with internal light. In this "waking state," a soft, velvety green bioluminescent moss is emerging from the wood grain (shell.shift). Camera: 85mm macro lens, f/2.8, shallow depth of field. High-resolution product photography. Lighting: A dual-lighting setup. Primary: A sharp, high-intensity "harsh flash" from the upper left, creating deep shadows and specular highlights on the polished wood. Secondary: A soft, pulsing volumetric internal glow of emerald green and violet (tide.phase) bleeding through the runes and moss. Material: Complex PBR layering. Polished, reflective dark wood texture with visible grain, contrasting with the soft, organic "subsurface scattering" of the glowing green moss. Small crystalline ice-flecks on the surface. Composition: Central hero shot, 45-degree isometric angle. The lantern sits on a rustic, weathered wooden workbench in the Kúlon-vrékil, surrounded by out-of-focus wood shavings and silver ink-pots. Style: A fusion of Y2K Frutiger Aero (clean, glossy, tech-organic) and "Cursed Dreamcore." The background is a liminal workshop space lit by distant, blurry aurora lights.

Luxury Cherry Product Photography Prompt (Black Diamond)

ecommerce-main-image

A detailed prompt for Nano Banana Pro, initially based on a 'banana' prompt but generalized for any product, specifically generating ultra-photorealistic macro photography of two luxurious cherries. The prompt includes technical details like lighting (jewelry photography), composition, and advertising copy for a 'Black Diamond' theme.

展开提示词全文
Subject: {argument name="subject" default="Two top-grade cherries, deep red, almost black"}, close together, with vibrant green stems connected. Details: Under a macro lens, the skin surface exhibits an extremely smooth, mirror-like texture, clearly reflecting the studio light source. A tiny, crystal-clear water droplet rests precariously on the roundest part of one of the fruits. Lighting: Fine professional jewelry photography lighting. Use a softbox to create sharp and clean long strip highlights, perfectly outlining the spherical curve and deep color of the fruit. Colors: Deep ruby red, ink black, highlight white, vibrant green (stem). Atmosphere: Extreme temptation, preciousness, luxury, mouth-watering. Technical Parameters: Macro photography, extremely shallow depth of field (focusing on the water droplet and highlights), 8K resolution, extreme sharpness, --ar 4:5 --v 6.0 [ 🖋️ Copywriting and Layout ]

Main Title: {argument name="main title" default="BLACK DIAMOND"}
Subtitle: 32mm+ Only for discerning palates.
Bottom Text: RARE & EXQUISITE
Layout Suggestion: Center alignment. Title uses a slender, elegant serif font, colored gold or white.

Multi-Language Figure Product Introduction Layout Prompt for Nano Banana Pro

ecommerce-main-image

A detailed JSON-like prompt structure designed exclusively for Nano Banana Pro to transform a reference image character into a collectible figure and present it in a professional product introduction layout. Users can customize the display language, product name, and manufacturer name.

展开提示词全文
[Figure Product Introduction Style Layout Prompt – Multi-Language Compatible Version]

This prompt allows you to transform a character from a reference image into a collectible figure
and present it in a product introduction–style layout.
The display language can be selected from four options:
Japanese, English, German, or French.

Please read this description carefully until the end.

※ This prompt is intended exclusively for Nano Banana Pro.
※ Unauthorized reproduction or redistribution of this prompt is prohibited.

◆ Overview

Display Language (language)
You can choose from:
- "ja" (Japanese)
- "en" (English)
- "de" (German)
- "fr" (French)

Product Name (product_name)
Manufacturer Name (manufacturer_name)

You may specify any arbitrary strings for both values.

Product Name Logo:
The product name logo is inferred from the product name string
and the visual atmosphere of the reference image.

Manufacturer Logo:
The manufacturer logo is inferred from the manufacturer name string.

※ Depending on the selected display language, these names may be translated
   or localized automatically.

Size:
The total height (in centimeters) is inferred and displayed
based on the character’s body proportions and the 1/7 scale setting.

Material:
Appropriate materials for a collectible figure are inferred and displayed.

Price:
The retail price is inferred from the figure’s scale,
modeling density, and paint detailing.

Close-Up Views:
Each close-up view is accompanied by a caption
that explains a different part or feature of the figure.
All captions are generated in the selected display language.

◆ How to Use

Display Language (language)
Rewrite the content inside the quotation marks ("") as shown below:

language: "{argument name="display language" default="en"}"

Available values:
ja: Japanese
en: English
de: German
fr: French

Product Name (product_name)
Manufacturer Name (manufacturer_name)

Rewrite the content inside the quotation marks ("")
using any arbitrary strings you like.

The manufacturer name will also be reflected
in the "Sculptor / Production" field.

product_name: "{argument name="product name" default="ARBITRARY_PRODUCT_NAME"}"
manufacturer_name: "{argument name="manufacturer name" default="ARBITRARY_MANUFACTURER_NAME"}"

◆ Precautions for Using This Prompt

This prompt does not intentionally include any specific work titles,
author names, character names, or brand names.

However, due to the internal processing or training data
of the image generation model, unintended associations may occur.
As a result, generated images may resemble existing works,
characters, trademarks, or brand logos.

Please exercise sufficient caution when using, publishing,
or distributing generated images.

We assume no responsibility whatsoever for any outcomes produced
by using this prompt, or for any issues, damages, or disputes
arising from such use.
All usage is at your own risk and discretion.

◆ Prompt
The full prompt for actual use is provided in the replies.

Visual Creator Mode Prompt for Product Photography (Precision vs. Decay)

ecommerce-main-image

A complex system prompt for Nano Banana Pro's 'Visual Creator Mode,' instructing the AI to act as a top visual creative director. It takes a JSON 'Creative Skeleton' input (here, focusing on mechanical keyboard keycaps, dust, and gears, with a tension of 'Precision vs. Decay') and optimizes it into a final, high-impact English image generation prompt for industrial product photography.

展开提示词全文
## 🎨 Visual Creator Mode

You are a top visual creative director with AI image generation capabilities.

I will provide a 'Creative Skeleton' randomly generated by a program, in JSON format. Your task is:

1.  **Interpret and Optimize**: Understand the various dimensions in the JSON (theme, tension, light/shadow, scene, etc.) and integrate them into a coherent, visually impactful concept.
2.  **First, display the optimized prompt**: Output the final image generation prompt you will use (in English, approximately 50-100 words) in a code block (```prompt ... ```).
3.  **Then, directly generate the image**: Use the above prompt to generate a high-quality visual work.

---

### Follow these principles during optimization:

-   **Resolve Conflicts**: If the dimension combination has logical contradictions (e.g., 'Industrial Photography' with 'Miniature Fantasy'), choose a dominant style and harmonize.
-   **Visual Anchor**: Translate abstract tension (e.g., 'Whimsical vs. Real Material') into concrete visual elements (e.g., melted chocolate flowing over precise metal gears).
-   **Viral Hook**: The image must have an unexpected detail that 'makes people want to look twice.'
-   **Style Tone**: If a `creative_directive` exists, use it as the emotional guidance for the image; if an `oblique_strategy` exists, use it as a structural constraint.

---

### Program Generated Creative Skeleton (JSON Input):
{
  "schema_version": "v1",
  "creative_id": "v9jrcpus",
  "creative_world": "world:product_photography",
  "creation_intent": "Form or Material Exploration",
  "creation_intent_id": "explore",
  "generation_logic": "The process or making itself is the highlight",
  "generation_logic_id": "process-driven",
  "twist_mechanisms": [
    "Scale Mismatch",
    "Cutaway Logic",
    "Material Swap"
  ],
  "twist_ids": [
    "scale_mismatch",
    "cutaway_logic",
    "material_swap"
  ],
  "subject_kit": {
    "primary_subject": "{argument name="primary subject" default="Mechanical Keyboard Keycaps"}",
    "primary_id": "a-mechanical-keyboard-keycap-set",
    "secondary_elements": [
      "Dust",
      "Tiny Gears",
      "Spec Label"
    ],
    "secondary_ids": [
      "element:dust",
      "element:tiny-gears",
      "element:spec-label"
    ]
  },
  "core_tension": "Precision vs Decay",
  "core_tension_id": "precision_vs_decay",
  "stage_context": "White Cyclorama",
  "stage_context_id": "white-cyclorama",
  "composition_rule": "Two-Object Comparison Layout",
  "composition_rule_id": "two-object-comparison-layout",
  "lighting_rule": "Three-Point Professional Lighting",
  "lighting_rule_id": "three-point-professional-lighting",
  "imaging_assumption": "Industrial Product Photography",
  "imaging_assumption_id": "industrial_product_photography",
  "deliverable_type": "Product Photo",
  "emergence": {
    "score": 2,
    "label": "Interesting Combo / Fun Combination"
  },
  "final_prompt": "Product Photo. featuring Mechanical Keyboard Keycaps, Dust, Tiny Gears, Spec Label. inspired by Precision vs Decay. with Scale Mismatch, Cutaway Logic, Material Swap. set in White Cyclorama. following Two-Object Comparison Layout. lit by Three-Point Professional Lighting.",
  "creative_directive": "Treat failure as the final work",
  "oblique_strategy": {
    "id": "reverse_assumption",
    "desc": "Reverse a fundamental assumption"
  },
  "validation": {
    "errors": [],
    "warnings": [],
    "dropped_overrides": []
  }
}

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。