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 577 条
Exploded Product Breakdown Image Generation Prompt
ecommerce-main-imageThis is a versatile prompt designed to generate a clean, top-to-bottom exploded breakdown image of any uploaded product or object, such as food, watches, or general products. It is intended to be part of a workflow that later uses the generated image and the original product image to create an 'Assemble → Exploded → Assemble' video using tools like Kling O1.
展开提示词全文
A clean, top-to-bottom exploded breakdown of the uploaded image, showing all components separated and aligned vertically, against a pure white background, minimal shadows, studio lighting, high detail, photorealistic, 8k, product photography, {argument name="product type" default="watch"}
3D Hagoita (Japanese Battledore) Image Generation Prompt
ecommerce-main-imageA detailed Japanese prompt designed for the Nano Banana Pro model to generate a high-quality, vertical portrait image of a three-dimensional Hagoita (Japanese traditional battledore) featuring a character motif. The prompt emphasizes the 'Oshie' (appliqué) technique, luxurious materials like gold leaf and silk, dynamic composition, and specific details like a calligraphic sign and decorative accessories, all presented within a glass case. It is structured with placeholders for customizing the character's features, clothing, and the text on the sign.
展开提示词全文
{argument name="Character features from reference image" default="The woman in the attached image. Regenerate her to look sexy."}: The woman in the attached image. Regenerate her to look sexy.
{argument name="Attire" default="The luxurious kimono in the image"}: The luxurious kimono in the image
{argument name="Sign text" default="lion"}: lion
A high-quality photograph of a traditional Japanese New Year's decoration, a 'Hagoita' (battledore), displayed inside a glass case with a luxurious white wood frame.
The image is a vertical portrait size suitable for a smartphone screen.
Angle and Composition:
The Hagoita is captured from a 'diagonal front' angle. By applying an angle instead of a straight front view, the thickness of the Hagoita and the three-dimensional relief of the 'Oshie' (appliqué) are emphasized, creating a sense of depth.
Hagoita Design:
In the center of the Hagoita, a three-dimensional character created using the traditional Japanese craft technique 'Oshie' is placed.
Character Features: {argument name="Character features from reference image" default="The woman in the attached image. Regenerate her to look sexy."} The character is not full-body; only the 'upper half' is largely sculpted. The feet and hem are not depicted.
Character Attire: Made from vibrant, textured Japanese fabrics (Chirimen or Kinran) in the style of {argument name="Attire" default="The luxurious kimono in the image"}.
The sleeves and decorations of the kimono have a dynamic design, significantly extending beyond the physical edges of the board to the left and right, spreading into the air. The fabric is layered, creating an overwhelming sense of volume and three-dimensionality.
Background Board Surface: The surface of the board behind the character is not plain wood but is lavishly decorated with 'gold leaf' or 'gold-painted designs of cherry blossoms and fans,' making it gorgeously ornate. Traditional Japanese patterns cover every space, making it extremely brilliant.
Handle (Grip): The handle part is not just a wooden stick but is decorated with 'black lacquer' with gold patterns, or wrapped with beautiful 'decorative cords' and 'tassels.'
Accessories:
A decorative 'Temari' (handball) is placed at the base of the Hagoita.
A white wood stand (tate-kanban) is placed next to (in front of) the Hagoita. The stand also has thickness, and the wood texture is realistic.
[IMPORTANT]: The text on the stand is artistically written in a 'masterful, flowing brush script (Gyosho style)' as if written by a skilled craftsman, spelling out "{argument name="Sign text" default="lion"}". The style conveys the blurring of the ink and the force of the brush.
Background and Atmosphere:
The background of the glass case features light pink and gold Japanese patterns (cherry blossoms or flowing water motifs).
There is light reflection on the glass case, and high-quality, luxurious lighting illuminates the piece.
Photorealistic style, 8k resolution, extremely detailed.
Hyper-realistic cinematic portrait for product detail page
ecommerce-main-imageThis is a detailed image generation prompt designed for a high-end product detail page (PDP) layout. It specifies a hyper-realistic, cinematic portrait of a glamorous Eurasian woman showcasing a prominent emerald wristwatch, complete with precise instructions for lighting (Rembrandt), composition (Web PDP style), accessories, and technical details (8k resolution).
展开提示词全文
Facing the right side of the frame, body angled slightly forward, hyper-realistic cinematic portrait of a glamorous {argument name="ethnicity and gender" default="Eurasian woman"} in her late 20s, showcasing a high-end {argument name="product" default="emerald wristwatch"}.
[Angle & Gaze]: Explicitly facing towards the right side of the canvas, 3/4 view, sultry gaze directed slightly downward, captivating expression.
[Face & Expression]: Alluring expression with slightly parted glossy lips, dewy makeup, defined cheekbones, long dark eyelashes, flawless porcelain skin texture.
[Accessories]: Emerald and diamond encrusted wristwatch (prominent), sparkling diamond stud earrings, delicate gold necklace visible.
[Outfit]: Elegant black velvet gown (off-shoulder, emphasizing curves), bare shoulders, graceful posture.
[Layout & Structure]: Web PDP (Product Detail Page) style layout with asymmetric composition. Product Gallery (left), Buy Box (right). Main image, thumbnails for detail, color, and lifestyle shots.
[Lighting & Atmosphere]: Rembrandt lighting, moody atmosphere, dark background with subtle light shafts, shallow depth of field, bokeh from distant chandeliers.
[Technical]: 8k resolution, highly detailed, photorealistic, sharp focus on watch and face, soft skin texture.
A stylish handwritten signature **'{argument name="signature name" default="Isabella"}'** is elegantly placed at the **Bottom Right corner**.
Negative prompt: facing left, looking left, body facing left, cartoon, illustration, anime, 3d render, blurry, distorted, bad anatomy, bad hands, missing fingers, extra fingers, text, watermark, bright lighting, cheerful atmosphere, no jewelry, plain clothes.. A stylish handwritten signature Willy is elegantly and small letters placed at the Bottom Right corner
Hand-carved wooden miniature figure prompt
ecommerce-main-imageAn image generation prompt designed to create a highly detailed, hand-carved wooden miniature figure of a specified subject. The prompt emphasizes texture, visible knife marks, natural wood grain, and specific lighting and composition details, suggesting a high-quality, realistic render.
展开提示词全文
A hand-carved wooden miniature figure of {argument name="name" default="[NAME]"}, shaped with visible knife marks, natural grain texture, and smooth unfinished edges. Placed on a workshop table with carving tools, wood shavings, and soft warm directional lighting. 1080×1080.
Pixel Art Grid using Fruit Flat-Lay Photography Prompt
ecommerce-main-imageA highly constrained prompt for generating a professional overhead flat-lay photograph that mimics pixel art. The image uses two types of fruit (e.g., yellow lemons and green limes) arranged in a tight, seamless grid to form text and a graphic silhouette (e.g., '2026' and a running horse). The prompt enforces strict rules on object size, orientation, and grid alignment to ensure perfect pixelation and commercial quality.
展开提示词全文
# Scene and World
Professional top-down flat-lay photography, strictly 90-degree vertical overhead God's perspective;
Pure white background;
Studio soft lighting, uniform and clear light, no shadows, no vignetting
# Focus and Order
Absolute Subject: A grid matrix formed by tightly and neatly arranged [{argument name="background item" default="fresh yellow lemons"}] (the background item), filling the entire frame;
Grid Specification: {argument name="grid columns" default="27"} columns horizontally, and several rows vertically, forming a complete matrix;
Form of Expression: Using [{argument name="contrast item" default="green limes"}] (the contrast item) with stark color contrast embedded to form a clear pixel art pattern;
Visual Logic: The upper half of the frame is the pixelated "{argument name="text content" default="2026"}" formed by the contrast item, and the lower half is the pixelated silhouette of the {argument name="graphic content" default="running horse"} formed by the contrast item;
Arrangement Constraint: All objects are exactly the same size, uniformly oriented (stems pointing the same way), tightly and seamlessly fitted together, absolutely no blank areas allowed
# Form and Structure
Upper composition: Pixelated "{text content}" using the contrast item, employing a monospace font where each character occupies the same number of columns;
Lower composition: Pixelated silhouette of the {graphic content} using the contrast item;
Perfect overhead 90-degree flat-lay perspective, camera lens axis strictly perpendicular to the ground;
Every object is whole, objects at the edge of the frame are not cropped, presenting a neat grid array;
Pixel art pattern is clearly discernible, edges are sharp;
Dense grid layout of {grid columns} columns × multiple rows, objects tightly filled, no gaps whatsoever
# Material and Language
Main Material: Real [{background item}] (smooth surface, natural reflection, fine texture, all objects uniformly oriented);
Contrast Material: Real [{contrast item}] (full color, fine surface texture, real details, all objects uniformly oriented);
Background: Pure white plane;
All objects are uniform in size, shape, and orientation, with no size differences or deformation
# Source of Tension
Natural objects transformed into digital pixel art;
Combination of traditional still life photography and modern pixel patterns;
Strong color contrast between [{background item}] and [{contrast item}] creates clear pattern recognition;
8K quality, high resolution, commercial advertising photography style;
Objects are absolutely regular in arrangement, pixel pattern is highly readable
# Technical Constraints (Ensuring Stability)
- Strictly 90-degree overhead angle, no perspective distortion
- Objects at the edge of the frame must be complete, not cropped
- The diameter of every object must be exactly the same, as if made from the same mold
- All objects must be uniformly oriented, stems or tops pointing consistently
- Clear grid structure: {grid columns} columns horizontally, and corresponding rows vertically, forming a strict rectangular grid
- Grid arrangement must be neat, aligned horizontally and vertically, with each cell the same size
- Objects must be tightly and seamlessly joined, absolutely no blank areas or gaps allowed
- Edges of the pixel pattern must be sharp and crisp
- Light is uniform, no local overexposure or underexposure
- Each character uses a monospace pixel font, all characters occupy the same number of columns
- Each object acts as one pixel unit, must be exactly the same size and uniformly oriented
Nano Banana Pro Prompt for Miniature Sneaker Scene
ecommerce-main-imageA structured prompt for the Nano Banana Pro tool, designed to generate a miniature scene featuring a sports shoe. The prompt uses a JSON format to specify the commercial intent, subject elements like miniature climbers and shoelace ropes, composition rules like forced perspective, and industrial product photography lighting for a macro kitchen countertop setting.
展开提示词全文
{
"creation_intent": "{argument name="creation intent" default="Commercial Persuasion"}",
"generation_logic": "Centered on people or characters",
"subject_kit": {
"primary_subject": "{argument name="primary subject" default="Sports Shoe"}",
"secondary_elements": [
"Miniature climbers",
"Shoelace ropes",
"Sole texture terrain"
]
},
"core_tension": "Containment vs. Infinity",
"twist_mechanisms": [
"Keycap world",
"Cross-section logic",
"Book stage"
],
"stage_context": "{argument name="stage context" default="Kitchen countertop macro scene"}",
"composition_rule": "Forced perspective layering",
"lighting_rule": "Warm practical light with soft shadows",
"imaging_assumption": "Industrial product photography",
"deliverable_type": "Miniature scene"
}
Gorpcore Editorial: Extreme Worm's-Eye View of Hiking Boot
ecommerce-main-imageA highly detailed prompt for generating an ultra-photorealistic, high-end gorpcore editorial image. It captures an extreme worm's-eye view of a technical hiking boot stepping in snow and mud, using direct flash photography at twilight to create a dark, moody, high-contrast aesthetic.
展开提示词全文
{
"meta": {
"aspect_ratio": "4:5",
"quality": "ultra_photorealistic",
"resolution": "8k",
"camera": "Sony A7R IV",
"lens": "16mm ultra-wide angle macro",
"style": "high-end gorpcore editorial, flash photography in nature, dark moody aesthetic, tactile realism"
},
"scene": {
"location": "rugged mountain terrain at twilight",
"environment": [
"dark snowy landscape",
"patches of moss and dry grass in extreme foreground",
"gnarled bare tree branches in silhouette",
"overcast dark blue sky"
],
"time": "blue hour / dusk",
"atmosphere": "cold, adventurous, cinematic gloom, heavy atmosphere"
},
"lighting": {
"type": "direct flash photography",
"key_light": "strong camera-mounted flash illuminating the sole and pants",
"ambient_light": "very low natural blue skylight",
"contrast": "high contrast between the illuminated shoe/legs and the dark background",
"shadows": "deep, crushing shadows in the upper frame",
"reflection": "subtle wet highlights on the rubber sole and synthetic fabric"
},
"camera_perspective": {
"pov": "extreme worm's-eye view (ground level)",
"angle": "looking straight up at the heel",
"framing": "macro focus on the shoe sole, legs towering above",
"distance": "immediate foreground (<10cm from the sole)",
"motion": "frozen mid-step action, dynamic walking pose"
},
"subject": {
"type": "hiker / outdoor explorer",
"orientation": "walking away from camera",
"focus_point": "right foot shoe sole",
"outfit": {
"pants": {
"type": "technical oversized cargo trousers",
"material": "waterproof GORE-TEX or nylon",
"color": "dark navy or black",
"texture": "crinkled, baggy fit, gathering around the ankles",
"details": "visible fabric tension and folds"
},
"jacket": {
"type": "heavy down puffer jacket",
"color": "black",
"fit": "oversized, bulky silhouette"
},
"backpack": {
"type": "technical hiking pack",
"visibility": "partial, black, sitting high on back"
}
},
"footwear_details": {
"type": "chunky technical hiking sneaker / boot",
"color": "off-white / cream outsole",
"sole_design": "aggressive traction lugs, deep grooves",
"branding": "distinct yellow octagonal Vibram logo embedded in the mid-sole",
"condition": "slightly used, traces of wet mud and snow in the treads",
"texture": "matte rubber with granular detail"
}
},
"details": {
"foreground_textures": {
"ground": "mixture of melting snow, dark soil, and reddish-brown moss",
"plants": "sharp focus on small twigs and moss directly under the shoe"
},
"imperfections": [
"mud specs on the white sole",
"uneven stitching on the pants",
"natural fabric bunching",
"film grai"
]
}
}
Ultra-Realistic Beverage Product Photography (Lemonate)
ecommerce-main-imageA prompt for generating ultra-realistic product photography of a chilled aluminum soda can, featuring a custom 'Lemonate' label, floating in crystal-clear blue water with dynamic ripples and condensation droplets.
展开提示词全文
Ultra-realistic premium beverage product photography of a chilled aluminum soda can floating upright at the center of the frame, partially submerged in vivid crystal-clear blue water, with dynamic ripples and splashes radiating outward; the can features a clean yellow-and-white label design with condensation droplets across the surface, and the brand name “{argument name="brand name" default="lemonate"}” prominently displayed in bold black typography, replacing all original branding, with smaller minimalist.
Ultra-Realistic Beverage Product Photography
ecommerce-main-imageA prompt for generating ultra-realistic product photography of a chilled aluminum soda can, featuring a custom 'Lemonate' label, floating in crystal-clear blue water with dynamic ripples and condensation droplets.
展开提示词全文
-Ultra-realistic premium beverage product photography of a chilled aluminum soda can floating upright at the center of the frame, partially submerged in vivid crystal-clear blue water, with dynamic ripples and splashes radiating outward; the can features a clean yellow-and-white label design with condensation droplets across the surface, and the brand name “{argument name="brand name" default="lemonate"}” prominently displayed in bold black typography, replacing all original branding, with smaller minimalist
Luxury Fukubukuro (Lucky Bag) Advertisement Key Visual Prompt
ecommerce-main-imageA highly detailed prompt for Nano Banana Pro to generate a photorealistic advertisement key visual for a custom 'Fukubukuro' (lucky bag) featuring an original character. The prompt mandates a high-end department store ad quality, focusing on composition where the bag is central, contents are scattered around, and text/product names are integrated as visual elements to create a sense of mystery and desirability.
展开提示词全文
Character Name: {argument name="Character Name" default="[Your Character Name]"}
## Key Visual Generation Prompt for Advertising/Posters/Promotional Materials (Lucky Bag Edition)
### 0. Primary Goal of This Prompt (Highest Priority)
This prompt is intended to generate **"photorealistic images of lucky bags" and key visuals for advertisements, posters, and promotional materials for department stores, specialty shops, and limited sales.**
The generated image must satisfy the following priorities:
* A level of completion that is instantly recognizable as an "advertisement."
* The lucky bag must function as the "main product," while the surrounding contents, world view, and character elements intensely boost anticipation and narrative.
### 1. Overall Premise of the Visual (Advertising Declaration | Boost Design)
This key visual is based on an advertising design where the direction of expression varies greatly, starting from the characteristics of the reference image. Do not aim for a stable solution; instead, extract the strongest element among luxury, excitement, strangeness, humor, chaos, or specialness, and elevate it into a **high-quality, high-sense, and "genius expression that makes you want it even though all the contents are visible."** It is an absolute condition that it functions as an "advertisement valid at a department store's first sale." This boost result is consistently reflected in the composition, placement of contents, product name display, and copy.
### 2. Scene/Moment (The Moment Cut Out for Advertising)
Automatically select the moment that has the highest appeal as an advertisement and instantly conveys "what kind of experience the lucky bag contains."
* The lucky bag may be opened.
* It may be half-open with contents spilling out.
* The contents may be beautifully arranged around the lucky bag.
**In this prompt, the composition with "the lucky bag at the center, with contents spread around it" is prioritized.**
Cut out a state where, upon first glance,
"What's inside?"
"But it's not ordinary."
"I want this."
all arise simultaneously.
### 3. Composition/Shooting Style (Advertising Layout Premise)
* Place the lucky bag in the center to slightly foreground of the screen.
* Frontal to slightly overhead angle suitable for advertising.
* Arrange the contents around the lucky bag in a circular, radial, or floating manner.
* Place product name text near or overlapping each item.
* Ensure intentional negative space for placing copy and year.
**Technical Requirements:**
* 8K resolution
* Ultra-realistic product photo
* Department store advertisement quality
### 4. Lucky Bag Package Design
The lucky bag is designed as the "outer shell" that most purely reflects the characteristics of the reference image.
* Basically, a shape that is valid as a department store, long-established shop, or brand lucky bag.
* Material (paper, cloth, Japanese paper, vinyl, luxury textile, etc.) is free.
* Change freely between luxury/pop/strange/festive/foreign object feeling, depending on the impression of the reference image.
### 5. Contents (Product Persuasiveness)
The contents of the lucky bag are not fixed by genre and are reconstructed based on the reference image and concept.
* Products that seem real.
* Products that are impossible.
* Characterized products.
* Products with strange sizes.
may be mixed.
The important thing is to establish the feeling that **"I can see everything, but it's mysterious and I want it."**
### 6. Character Expression (Inhabitants of the Lucky Bag World)
The character exists naturally within the contents of the lucky bag or the surrounding world.
* May be composed of products.
* May be jumping out of the lucky bag.
* May be in a pose introducing the contents.
Exclude any artificial feeling,
Treat them as "beings who originally live in this lucky bag world."
### 7. Color Scheme
The color rules are not fixed; the optimal solution is automatically selected based on the reference image and concept.
* Express value not through color, but through texture, density, gloss, and information volume.
* The lucky bag, products, characters, and background should not clash, yet be excessively lively.
### 8. Advertising Copy/Product Name Display (Most Important)
Copy and product names naturally arise as a result of verbalizing the reference image and concept.
* Directly display "Product Name Text" next to each item placed around the lucky bag.
* Product names allow for naming that is high-sense/intensely humorous/barely nonsensical.
* Year
* Lucky Bag Title
* Words like Limited/First Sale/Carefully Crafted
* Price notation
Are placed in the most beautiful and most insane arrangement for an advertisement.
Treat text as a **visual element, not information.**
### 9. Variation Display (For Advertising)
* Display lucky bag variations like Pine/Bamboo/Plum
* Normal/Deluxe/Insane
In a wipe-style display.
* Small frame
* Lucky Bag Name + Price
* Size that does not obstruct the main subject
---
### 10. Background/Light
* Bright, hopeful light of the first sale.
* Changes to gorgeous/pop/strange/serene, depending on the reference image.
* Maximize the texture of materials, logos, and the edges of text.
---
### 11. Final Tone (Output Guideline)
**Looks genuinely for sale,
all contents are visible,
yet clearly not ordinary.**
Character x Lucky Bag x Advertising Key Visual
Completed form.
Macro Product Shot of Seltzer Can
ecommerce-main-imageA prompt for generating a vibrant, ultra-detailed macro product shot of an ice-cold lime seltzer can balanced on a wet, sun-drenched pool deck, focusing on texture, water beads, and a strong shadow for a summer commercial aesthetic.
展开提示词全文
A vibrant, ice-cold lime seltzer can balanced on a wet, sun-drenched pool deck. Water beads cling to the can’s matte texture. A strong shadow defines the ground. Ultra-detailed, macro product shot, vibrant color palette, summer commercial aesthetic
A detailed prompt for generating a photorealistic image of a nano-banana-pro
ecommerce-main-imageThis is a highly detailed image generation prompt used to compare the output quality of different AI models (Imagen 4, ChatGPT, and Nano banana pro). The prompt requests a photorealistic, high-resolution image of a nano-banana-pro, emphasizing specific visual details like texture, lighting, and background.
展开提示词全文
photorealistic, high resolution, 8k, ultra detailed, a nano-banana-pro, on a {argument name="surface" default="wooden table"}, soft studio lighting, macro lens, shallow depth of field, {argument name="background" default="minimalist background"}, cinematic lighting, detailed texture, volumetric light, highly detailed, sharp focus, {argument name="style" default="photorealistic"}
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。