← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 2,041 · 热度分 56.4

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 5717 条

Cinematic Artisan Portrait Prompt for Model Making Workshop

product-marketing

This detailed prompt is designed to generate a cinematic, National Geographic-style portrait of a craftsman working on a miniature model of a famous structure, like the Death Star. It specifies the aesthetic, materials, lighting, and composition to create a highly atmospheric image of a cluttered workshop.

展开提示词全文
Do this for {argument name="structure name" default="Death Star"}: <instruction>
  1. The Semantic Inference Engine (The Masterpiece):  
Input A is a Famous Building, City, or Fictional Structure (e.g., The Colosseum, Hogwarts, The Death Star).
Analyze the subject to determine the   Model Aesthetic  :
   The Material:  Identify the primary modeling medium.
   (e.g., Ancient Ruins -> Plaster/Clay. Modern City -> White Foamcore/Acrylic. Fantasy -> Wood/Moss). 
   The Blueprints:  Identify the reference documents on the table.
   (e.g., Vintage Parchment Maps vs. Blue Cyanotypes vs. Digital CAD printouts). 
2.  The Workshop :
Goal: "Cinematic Artisan" Portrait.
The Room: A cluttered, high-ceilinged Model Maker's Studio. Wooden shelves line the walls, filled with "Previous Projects" (other models in the same genre).
The Character: an input inspired maker character wearing a relevant apron and an appropriate Visor or protective tool
The Table: A scarred wooden workbench covered in scale modeling tools: X-Acto knives, glue bottles, sanding blocks, and sawdust.
3. The Narrative :
The Pose: The craftsman is leaning in close to the "Model" (Input A), which sits centrally on the table.
The Interaction: He is delicately placing a Tiny Detail Component onto the structure using tweezers or his fingers.
(e.g., Planting a miniature tree, placing a tiny flag, or gluing a microscopic figure).
The Scale: The model looks grand but miniature; the human hands look massive and weathered in comparison.
4. Lighting & Atmosphere:
Lighting: Volumetric God Rays (Tyndall Effect). A strong, singular shaft of warm sunlight streams in from a high window (top left/center), illuminating the floating dust particles and spotlighting the model.
Contrast: The workshop corners are in deep shadow; the work surface is bright.
Palette: Warm, dusty Earth Tones (Browns, Golds, Beiges).
Output: ONE image, 16:9 Aspect Ratio, Cinematic Photography, "National Geographic" aesthetic, Volumetric Lighting.
</instruction>

Ultra-Realistic Exploded Pizza Infographic and Motion Prompt

product-marketing

This prompt set is for generating ultra-realistic food photography, including a motion prompt for video generation (Kling AI) and two image prompts: one for a standard, high-detail pizza slice, and another for an exploded infographic view of the pizza layers.

展开提示词全文
Motion Prompt: The Pizza start to round spin while ingredients separate gently and precisely, maintaining alignment and scale. The motion is smooth, with no extra effects.

Image 1 :- Ultra-realistic prepared pepperoni pizza slice, fully assembled, gooey melted mozzarella cheese stretching and dripping over the edges, crispy pepperoni slices on top, rich tomato sauce beneath, thick golden baked crust, fresh basil leaves and light seasoning floating subtly above, clean pure white background, professional commercial food photography lighting, soft natural shadows under the slice, sharp focus, extreme texture detail, glossy cheese, crunchy crust surface, studio shot, minimal composition, no text, no labels, no hands, premium food advertisement style, 8K resolution, ultra-detailed, hyper-realistic.

Image 2 :- Produce an ultra-realistic exploded pizza slice infographic. Top layer features basil leaves and seasoning particles floating. Below are melted cheese stretch, pepperoni slices, rich tomato sauce layer, soft baked crust base. Clean white background, professional food photography lighting, realistic textures, gentle shadows, floating layers evenly spaced, labeled infographic style, 8K resolution.

Surreal High Fashion Editorial Prompt with Living Insects

product-marketing

A highly detailed, structured prompt for Gemini Nano Banana Pro focused on generating a surreal, high-fashion editorial image. The scene is set in an overgrown Victorian greenhouse atelier, featuring a 'Restless Creator' tailoring a garment adorned with living, jewel-toned beetles and Atlas moths. The prompt specifies technical details like telephoto compression (Hasselblad H6D-100c), Kodak Ektar 100 film aesthetic, and heavy foreground occlusion to create a voyeuristic, humid atmosphere.

展开提示词全文
{
  "vibe_title_en": "Symbiotic Insect Atelier",
  "master_prompt": "A voyeuristic, telephoto capture through the condensation-streaked glass of an overgrown Victorian greenhouse turned chaotic couture atelier. The Protagonist, characterized as a restless creator with messy hair and rolled-up sleeves, is frozen in a moment of intense, sweaty focus. They are meticulously tailoring a garment where the embroidery is alive; shimmering, jewel-toned beetles crawl in organized patterns across the fabric, acting as living sequins, while giant, sympathetic Atlas moths rest gently on the subject's shoulders like royal epaulets. The environment is dense and cluttered: piles of botanical sketches, antique taxidermy tools, spools of raw silk, and moss reclaiming the furniture. Lighting is dappled and atmospheric, cutting through the humidity. Shot on a Hasselblad H6D-100c with a 210mm lens for extreme compression, creating a shallow depth of field that blurs the foreground foliage. The aesthetic mimics Kodak Ektar 100 film with rich, saturated greens and golds, emphasizing the hyper-realistic texture of insect wings and human pores. No neon, practical effects style.",
  "meta": {
    "intent": "Editorial High Fashion Surrealism",
    "priorities": "Photorealistic Texture, Narrative Density, Surreal Integration",
    "device_profile": "Hasselblad H6D-100c"
  },
  "frame": {
    "aspect": "4:5",
    "composition": "Voyeuristic telephoto compression with heavy foreground occlusion (leaves/glass)",
    "layout": "Centered subject framed by environmental clutter",
    "camera_angle": "Eye level, shooting through a barrier",
    "tilt_roll_degrees": "0"
  },
  "subject": {
    "gender": "Female",
    "identity": "The Restless Creator / Insect Queen",
    "demographics": "Adult, Universal Model Template",
    "face": "Intense focus, beads of sweat, minimal makeup, natural skin texture",
    "hair": "Slightly messy, unkempt, possibly interacting with insects",
    "body": "Leaning forward in concentration, active posture",
    "expression": "Deep concentration, mouth slightly parted in focus",
    "pose": "Mid-action, adjusting a garment or inspecting a specimen"
  },
  "wardrobe_accessories": {
    "garments": [
      {
        "item": "Couture Gown/Robe",
        "material": "Raw Silk and Organza",
        "color": "Pale Cream and Earth Tones",
        "fit": "Draped, Voluminous"
      }
    ],
    "accessories": [
      {
        "item": "Living Jewelry",
        "color": "Iridescent Green and Gold",
        "material": "Real Beetles and Moths",
        "brand_style": "Surrealist High Fashion"
      }
    ]
  },
  "environment": {
    "setting": "Overgrown Greenhouse Atelier",
    "surfaces": "Mossy wood, dirty glass, velvet, paper stacks",
    "depth": "Deep layered depth due to foreground occlusion and background clutter",
    "atmosphere": "Humid, dusty, heavy air, sun-drenched but hazy",
    "lens_interaction": "Condensation on "
  }
}

Hyper-Realistic Commercial Food Photography Prompt

product-marketing

A detailed prompt for generating hyper-realistic commercial food photography, specifically focusing on high resolution, sharp focus, and controlled studio lighting to capture frozen mid-air action of ingredients. This prompt is structured using JSON for precise control over output settings and aesthetic details.

展开提示词全文
"resolution": "{argument name="resolution" default="8K UHD"}",

"aspect_ratio": "3:4",

{ "image_style": "{argument name="image style" default="hyper-realistic commercial food photography"}", "quality": "Ultra-high detail, sharp focus, studio-grade clarity", "lighting": "Soft but controlled studio lighting with visible highlights and splash definition", "motion": "Frozen mid-air action, ingredients suspended",

"global_settings": {

"background_style": "Solid or smooth gradient background, color varies per module", 
"camera": "High-speed photography look, shallow to medium depth of field", "post_processing": "Balanced contrast, natural saturation, no artificial glow" }}

Miniature Figure Generation: Everyday Life of 'Scissors Old Man'

product-marketing

This prompt generates miniature figures of a character known as the 'Scissors Old Man' engaged in various everyday activities. By slightly changing the prompt, users can visualize the character in different scenes, such as singing karaoke, shopping, reading, or working on a PC, emphasizing the detailed and playful nature of the output.

展开提示词全文
Create 4 patterns of miniature figures of the '{argument name="character name" default="Scissors Old Man"}'! ✨

🎤{argument name="activity 1" default="Solo karaoke"} 🛒{argument name="activity 2" default="Shopping at the supermarket"} 📖{argument name="activity 3" default="Reading"} 💻{argument name="activity 4" default="PC work"}

Just by slightly changing the prompt, the old man's daily life is embodied so realistically! The size and detail are irresistible (lol)

Transform Portrait into 3D Action Figure

product-marketing

A prompt designed for image-to-image transformation, instructing the AI to convert an uploaded portrait into a stylized 3D action figure. It specifies the style (glossy plastic toy, simplified features, big eyes) and the background (toy store shelf with blurred boxes), while requiring the main facial characteristics of the original person to remain recognizable.

展开提示词全文
Turn this portrait into a stylized 3D action figure of this person. Style: plastic toy with glossy finish, big eyes, simplified features. Background: toy store-style shelf with blurred boxes. Constraints: keep main facial characteristics recognizable.

Kimberly Garner in Yellow Bikini (Wet Look)

product-marketing

A structured JSON prompt for generating an image of British actress Kimberly Garner. It specifies her appearance, including wet, slicked-back blonde hair and a neutral expression, while detailing her bright yellow, high-cut bikini and the environment (clear blue water, sunny lighting) to create a relaxed, summery mood.

展开提示词全文
{
  "subject": {
    "name": "Kimberly Garner",
    "age": "young adult",
    "appearance": {
      "complexion": "fair",
      "hair": {
        "color": "blonde",
        "length": "long",
        "style": "wet, slicked back"
      }
    },
    "expression": "neutral",
    "pose": "standing in water, looking directly at the camera"
  },
  "clothing": {
    "bikini": {
      "color": "bright yellow",
      "top": {
        "style": "triangle",
        "straps": "thin, tie around neck and back"
      },
      "bottom": {
        "style": "high-cut, cheeky",
        "straps": "thin side ties"
      }
    }
  },
  "environment": {
    "location": "clear blue water",
    "background": "blur of blue water and sky",
    "lighting": "bright and sunny",
    "mood": "relaxed, summery"
  },
  "image_details": {
    "width": 504,
    "height": 1002,
    "orientation": "vertical",
    "lens": "Canon RF 100mm"
  }
}

Messi in Gen Z Fashion Portrait

product-marketing

A highly detailed prompt for generating a full-body fashion portrait of Lionel Messi in a Gen Z aesthetic, standing confidently on a rooftop parking lot. The prompt mandates using an uploaded image for the exact face reference, while describing a bold, color-blocked zip-up jacket, loose black pants, and colorful sneakers, blending realistic photography with subtle artistic flair.

展开提示词全文
A full-body fashion portrait of a young man standing confidently on an open rooftop parking lot under a clear blue daytime sky, with distant city buildings softly blurred in the background. He is positioned slightly angled toward the camera, weight shifted onto one leg, with both hands casually placed inside the pockets of his black pants, creating a relaxed yet stylishposture. His expression is calm and self-assured, with a subtle, composed gaze directed toward the camera.

He has a youthful face with smooth medium skin tone, a neatly groomed thin mustache, straight nose, defined jawline, and expressive eyes that convey quiet confidence. His hair is dark, thick, and neatly styled with volume, combed back and slightly to the side, giving a clean, polished look. He is wearing a bold, color-blocked zip-up jacket featuring vibrant red, blue, green, yellow, and black panels arranged in a geometric pattern, with a black ribbed collar and zipper running down the center. The jacket fits comfortably and stands out strongly against the neutral rooftop setting. He pairs it with loose-fitting black pants and colorful athletic sneakers that echo the playful color palette of the jacket. Around his body, subtle stylized graphic accents appear—small curved strokes and confetti-like shapes in matching bright colors—adding a modern, creative, illustrated effect without overpowering the realism of the photo. The lighting is natural and even, coming from daylight above, casting soft shadows and maintaining clear detail across his face and outfit. The overall mood is modern, youthful, energetic, and fashion-forward, blending realistic photography with light artistic flair. The camera is positioned at eye level, capturing a balanced, editorial-style composition with shallow depth of field that keeps the subject crisp while softly blurring the background. Use this uploaded photo as the only and exact face reference. The generated image must use this same face exactly as shown, without any changes to identity, facial structure, or expression.

Luxury Korean Hanbok Product Mockup (Symmetrical Flat Lay)

product-marketing

A highly specific prompt designed to generate a luxury product mockup of traditional Korean Hanbok items in a symmetrical, centered flat-lay composition. It mandates a seamless, pure white background and meticulously details the placement, color, and texture of every item, from the central crimson silk Jeogori to the surrounding accessories like the Bokjumeoni and Binyeo, aiming for a balanced, editorial commercial photography style.

展开提示词全文
A luxury Korean traditional Hanbok (한복) product mockup with perfectly balanced centered composition on seamless white background.

CANVAS & BACKGROUND - CRITICAL:
- Seamless infinity white backdrop fills entire frame edge to edge
- Background extends from corner to corner with no visible borders
- Clean warm white (#FFFAF5) continuous uniform tone across full canvas
- No vignetting, no falloff, no darkening at edges
- All four corners identical in color and brightness
- Even exposure across entire image from left to right, top to bottom
COMPOSITION - SYMMETRICAL CENTERED LAYOUT:
- Perfect center axis alignment
- Equal visual weight on left and right sides
- Products arranged in triangular hierarchy
- Minimum 10% margin between products and frame edges
BACK ROW (Top Center):
- CENTER-BACK: Matte black gift box with gold Dancheong border, 연꽃문 lotus embossed, "한스타일 Hstyle" in gold
- LEFT-BACK: Cream shopping bag with gold Taegeuk symbol
- RIGHT-BACK: Open box showing cream silk lining with gold crane pattern
MIDDLE ROW (Center Hero):
- EXACT CENTER: Crimson red silk Hanbok Jeogori (저고리) with gold peony embroidery on cream silk cloth, sleeves spread symmetrically, white collar (동정) visible
FRONT ROW (Evenly Spaced):
- LEFT: Traditional fan (부채) with plum blossom
- CENTER-LEFT: Plum blossom sprig
- CENTER: Royal blue Bokjumeoni (복주머니) with gold 福
- CENTER-RIGHT: Gold Binyeo (비녀) on cream cushion
- RIGHT: Plum blossom sprig
LIGHTING:
- Soft diffused overhead lighting
- Even illumination including all corners and edges
- No directional shadows toward frame edges
- Consistent brightness across full frame
CAMERA:
- Shot straight-on, camera perfectly centered
- 4:5 aspect ratio
- Products composed with safe margin from all edges
- Full frame background coverage
STYLE: Balanced editorial luxury, Korean heritage, commercial product photography
Negative prompt: vignetting, dark corners, uneven background, cropped edges, gradient falloff, visible backdrop edges, inconsistent lighting at borders
A stylish handwritten signature "Willy" in small gold letters at bottom right corner.

2x2 Grid of Ultra-Realistic Female Portraits

product-marketing

A highly detailed prompt for generating a 2x2 grid of ultra-realistic, high-resolution female portraits. Each panel features a different woman with specific hair, clothing, and accessory details (e.g., headphones, knit sweaters, jewelry), all unified by a theme of fair skin, rosy cheeks, playful winking, and cinematic lighting with pastel bokeh backgrounds.

展开提示词全文
2x2 grid of ultra-realistic, high-resolution photograph portraits of beautiful young women with fair skin and rosy cheeks, winking playfully, studio quality. 1: Top left: Shoulder-up shot, a stunning woman with long curly strawberry-blonde hair styled in a high bun, wearing white over-ear headphones and pastel pink sunglasses, pink oversized knit cardigan, fluffy cream crop top, light beige lounge shorts with a delicate pink bow. 2: Top right: Intimate headshot, a gorgeous woman with long wavy auburn hair cascading sensually down her shoulders, adorned with gold hoop earrings, wearing a chunky cream knit sweater, soft lavender eyeshadow enhancing her captivating eyes. 3: Bottom left: Alluring head and torso view, a striking woman with long straight platinum blonde hair styled in a high ponytail, a delicate silver chain necklace accentuating her neckline, wearing a powder blue cropped knit sweater, light, tasteful makeup. 4: Bottom right: Sensual close-up head and shoulders shot, a beautiful woman with long messy braided brunette hair adorned with delicate flowers, gold dainty earrings, a cozy forest green chunky knit sweater, natural, enhancing makeup. Warm, soft, and cinematic lighting with pastel bokeh backgrounds in each panel, shallow depth of field, ultra-detailed textures, soft global illumination, smooth skin shading, ultra-high resolution, 8K, sharp focus, clean, vibrant, aesthetic, studio quality. A stylish handwritten signature "Willy" is elegantly and small letters placed at the Bottom Right corner, realistic skin texture, professional photography, shot on Hasselblad X2D, 85mm f/1.2 lens.

Winter Fashion Landing Page Design and Editorial Image

product-marketing

A complex prompt that combines a request for a vertical-scroll landing page design layout with a highly detailed description of the main editorial image. The image features an ethereal Eurasian woman in a snowy birch forest wearing cream knitwear, emphasizing soft winter lighting, shallow depth of field, and a high-end fashion editorial style. The prompt also outlines the content and structure of four feature cards for the landing page.

展开提示词全文
Landing page design for a winter fashion collection, vertical scroll layout, full-bleed top image, feature cards below, stacked sections.

Editorial fashion portrait of a young Eurasian woman in her early 20s with a slim oval face and V-line jawline, standing in a snowy birch forest, long flowing wavy light brown hair with golden caramel highlights, delicate snowflakes in hair, large bright blue-green doe eyes with long natural lashes, luminous dewy porcelain skin with healthy glow, glass skin effect, soft rosy blush on cheeks, glossy pink lips with radiant smile showing perfect teeth, slim straight nose, delicate feminine features, ethereal doll-like beauty, wearing a cream cable knit oversized sweater, ivory knit scarf wrapped cozy around neck, matching beige knit gloves touching birch bark, wearing a long flowing pleated silk maxi skirt with a subtle floral pattern, elegant relaxed pose with gentle head tilt, soft dreamy expression, snowy birch forest background with beautiful bokeh, gentle snowfall, soft diffused winter lighting, shot on 85mm f1.4 lens, shallow depth of field, cool blue and warm cream tones, high-end fashion editorial style.

FEATURE CARDS:
- Card 1: "Timeless Elegance" - image of the woman in the forest, text describing the core values of the collection, CTA to "Explore the Collection"
- Card 2: "The Softest Cashmere" - close-up shot of the cashmere sweater, details on the material and craftsmanship, CTA to "Shop Sweaters"
- Card 3: "Winter Whites" - a selection of ivory and cream pieces from the collection, CTA to "Shop Whites"
- Card 4: "Designed for Comfort" - description of the relaxed fit and cozy designs, CTA to "Learn More"
A stylish handwritten signature "Willy" is elegantly placed in small letters at the bottom right corner.

2x2 Grid Product Invention Visualization (Patent/Marketing)

product-marketing

A complex, multi-panel prompt designed to visualize the invention and marketing of a new product by combining two concepts (or evolving one). It mandates a 2x2 grid structure, with each quadrant requiring a distinct visual style: technical line art (Exploded Patent View), schematic diagram (Functional Diagram), photorealistic render (Product Render), and editorial layout (Marketing Pitch). The prompt acts as an industrial designer, focusing on cohesion between the panels and a minimalist, consumer electronics aesthetic.

展开提示词全文
Input Variable: {argument name="input objects" default="[INSERT 1 or 2 OBJECTS]"} 
Instruction:
Act as a Visionary Industrial Designer and Patent Clerk. Create a 2x2 Grid visualizing the invention of a new product based on the Input.
 Innovation Logic  :
Analyze Functions: Identify the primary utility of Input A and Input B.
The Fusion: Combine them into a single, cohesive device that solves a specific (niche) problem.
If 2 Inputs: Hybridize them (e.g., Mug + Grater = A self-cooling mug with a garnish shaver).
If 1 Input: Evolve it (e.g., Toothbrush = A self-sanitizing, toothpaste-injecting smart wand).
The Branding: Generate a catchy, corporate product name (e.g., "The Breeze-Grate™", "Solar-Brella Pro").
The Visual Structure (The 2x2 Grid):
CRITICAL: The image must be split into 4 distinct quadrants with different visual styles.
Panel 1 (Top Left): The Exploded Patent View
Style: Black & White Technical Line Art. Thin distinct lines, no shading.
Content: An isometric "Exploded View" of the device, showing the internal motor, battery, or mechanism separated from the shell.
Detail: Add Numbered Leader Lines (10, 12, 14) pointing to specific parts.
Panel 2 (Top Right): The Functional Diagram
Style: Black & White Schematic with bold arrows.
Content: A cross-section or "In-Use" drawing showing how how the device works. Use Action Arrows to show airflow, rotation, or liquid movement.
Detail: Show the "Result" (e.g., cheese falling, water spraying).
Panel 3 (Bottom Left): The Product Render
Style: High-End Studio Photography. Color, Glossy, "Apple/Braun" Design Aesthetic.
Content: The final physical product sitting on a white reflective surface. It should look sleek, using materials like White Ceramic, Brushed Aluminum, or Matte Plastic.
Context: Include a small prop to show scale (e.g., a block of cheese, a coffee bean, a hand).
Panel 4 (Bottom Right): The Marketing Pitch
Style: Editorial Magazine Layout. White background, black text.
Typography:
Headline: Large, Bold Serif Text displaying the [Invention Name].
Body: A block of clean "Lorem Ipsum" or readable text describing the "Revolutionary Features."
Bullets: A small list of specs (e.g., "Dishwasher Safe," "USB-C").
Visual Syntax:
Cohesion: The product design in Panel 3 must perfectly match the line art in Panel 1.
Design Language: Minimalist, Ergonomic, Consumer Electronics aesthetic. Even if the idea is silly, the design must look expensive.
Output: 2x2 Grid, Mixed Media (Line Art vs. Photorealism), 8k Resolution, "Kickstarter Campaign" Aesthetic.
上一页 335 / 477 下一页

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。一节课的讲解也能做成课程口播。

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。

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。

海报设计工作室

免费增值需申请 Key

将一段活动描述、一张产品照片或品牌参考图,转化为抓人眼球的活动海报、宣传 banner 或社交媒体配图。这款 AI海报设计与制作工具生成图片丰富的海报,在海报排版上搭配清晰视觉层级、按品类匹配的风格和预留文字区域,覆盖活动、音乐节、电影、产品发布和促销场景。你可以把它当作 AI宣传单制作工具来制作促销宣传单,当作活动海报设计工具,当作电影海报生成器,当作音乐节海报设计工具,当作产品发布会海报的 banner设计 AI,或当作平面设计海报工作室。从活动主题出发,用品牌风格参考图变换产品或场景照片,或在已认可草稿上做定向精修,完成可印刷或可分享的成品。

自动化克隆数字人口播混剪视频

免费增值需申请 Key

抖音短视频双路径生产体系(单 Skill 版)。Path A[付费·高质量]:策略大脑→(可选:素材混剪/AI高光提取)→脚本优化→AI生图/素材准备→配音渲染(百炼/GPT-SoVITS/CosyVoice/VoxCPM2+剪映/Remotion/ffmpeg/数字人)。Path B[免费·动画风]:采集热点→脚本→edge-tts免费配音+HyperFrames开源渲染→MP4,零云费开箱快。触发词分层:①"抖音短视频/选题规划/合规闸门/运营策略" ②"口播脚本/AI生图/AI配音/视频渲染/Remotion渲染" ③"蹭热点/快速出片/免费做视频" ④"混剪/高光提取/素材粗剪/autoclip

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。