← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 1.8K · Heat 55.6

Introduction

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。

Resource Information

Author:dophinl
Category:Multimedia
Version:1.0.9
Auth: No auth
Pricing: Not specified

License information is collected from official sources and may be outdated or missing. Refer to the LICENSE file in the original repository before commercial use.

Tags
图片生成

Prompt Library · 22.8K

Source: community prompt library (MIT, synced daily)

15141 distinct prompts across 11 use cases; one prompt may serve several, so category counts add up to more than the deduplicated total.

725 matches

Cyberpunk Spider-Man in Matte Black and Gold

game-asset

A descriptive prompt for generating an image of a luxury, high-tech cyberpunk version of Spider-Man. The suit is matte black with gold neon accents and carbon fiber texture. He is leaning against a chrome sports hoverbike on a rooftop helipad overlooking a glittering city skyline.

Show full prompt
{
  "prompt": "Luxury high-tech cyberpunk Spider-Man in a sleek matte black suit with gold neon accents and carbon fiber texture. Leaning against a chrome sports hoverbike on a rooftop helipad, city skyline glittering below. Mask lenses displaying golden holographic interfaces, confident pose, elegant and expensive aesthetic, sharp details, teal and gold color scheme."
}

Child's Drawing to 3D Image Prompt

game-asset

A simple prompt used with Nano Banana Pro to transform a child's drawing into a polished, colored 3D image.

Show full prompt
Turn this image into a polished 3d image (with color)

Texture Creation via JSON and UV Map Metaprompt

game-asset

A two-step process for creating textures using Nano Banana Pro. First, an existing image (e.g., flower, clothing pattern) is analyzed by ChatGPT and converted into a detailed JSON prompt describing its size, color, shape, and details. Second, this JSON is fed into a specialized metaprompt designed for UV mapping, instructing Nano Banana Pro to paint the texture onto a UV deployment map, similar to Substance Painter.

Show full prompt
First, analyze **the source image (flower, clothing, pattern, etc.)**.

Instruction to ChatGPT:

"Convert this image into a JSON prompt, including size, color, shape, and details."

Instruction: "Metaprompt Goal: Create a prompt for NanoBananaPro that draws the specified texture onto a UV deployment map. Perform a process similar to Substance Painter, generating the texture by referencing image 2 against the UV map. Based on this JSON, create a prompt to change the color by referencing an additional image. Aim to create a prompt template in JSON format that generates a skirt texture on a UV map. Clearly instruct NanobananaPro to create the color based on this image. Generate a single prompt JSON according to a predefined JSON schema: ..."

Generate Dice Faces with Specific Object Placement

game-asset

A technique for Nano Banana Pro to generate the faces of a die, ensuring that objects (like a portrait) are placed accurately on the faces by providing an input template that specifies the positions of the pips.

Show full prompt
Generate the faces of a die.

Only the '1' face is replaced with my portrait.

An input template indicating the positions of the pips is provided so that objects are placed on the die faces as intended.

Photorealistic Close-Up of Spider-Man Cosplay

game-asset

A detailed prompt with positive and negative instructions for generating a photorealistic close-up portrait of a person wearing a highly specific Spider-Man cosplay suit (Andrew Garfield version). It focuses on intricate fabric textures, reflective lenses, and cinematic photography style against a blurred stone wall background.

Show full prompt
{
  "prompt": "photorealistic close-up portrait of a person wearing a highly detailed Spider-Man cosplay suit from The Amazing Spider-Man films (Andrew Garfield version), full-head red morphsuit with black raised webbing pattern and subtle hexagonal texture on the red fabric, large oval black-framed lenses with raised edges, silver perforated mesh covering the eyes, reflective white highlights on lenses, silver-and-black spider emblem centered on chest, blue fabric sections visible on lower arms, high collar covering neck, no skin visible, dramatic heroic pose with head tilted upward gazing into the distance, blurred gray stone wall background, natural daylight lighting, sharp focus, intricate fabric details, realistic textures, high resolution, cinematic photography style",
  "negative_prompt": "cartoon, animated, drawing, illustration, low quality, blurry, deformed, ugly, bad anatomy, extra limbs, visible face, visible skin, open mouth, teeth, eyes visible through mask, watermark, text, logo, overexposed, underexposed, artifacts"
}

Game/Book Diorama Concept Generator

game-asset

A system prompt instructing the AI to act as a world-class visual artist and content generator. Its task is to analyze the core identity of a game or book and construct a high-concept diorama inside a hollowed-out, context-appropriate shell. The diorama must feature miniature elements, assets, and characters from a famous level or scene, with lighting and style matching the source material.

Show full prompt
<instructions> you are a world class visual artist and viral content generator tasked with creating high-concept diorama for games or books. For every input, you will analyze the core identity, the defining artifacts, the atmosphere, characters and the underlying narrative of the subject. you will then construct a specific container, the appropriate shell based on the title and year it was made: for any title, analyze the mechanics and aesthetic. visualize a hollowed-out item. the interior is a diorama of a famous level or scene. it contains miniature elements, assets, tiny protagonist, and other relevant elements to the subject. lighting & style should be appropriate for the title </instructions>

Kitchen Utensil to Interstellar Warship Transformation

game-asset

A complex, multi-step prompt for transforming a common kitchen utensil (e.g., a meat cleaver) into a colossal, brutalist interstellar warship for an evil galactic empire. The output is a 2x2 contact sheet grid featuring a technical blueprint, a 3D cross-section, an exterior deep space shot, and an interior bridge shot, all rendered with tactical realism and a Denis Villeneuve/Jony Ive aesthetic.

Show full prompt
Do this for {argument name="utensil" default="meat cleaver"}: 
Task: Pick a utensil that is uploaded or given, Transform it into a colossal, fully operational interstellar warship for an evil galactic empire.

Step 1: user uploads image of a kitchen tool or utensil

Step 2: Analyze the object’s geometry, holes, curves, and functional part and design ship parts based on that 

Step 3: Scale up 10,000x into a moon-sized dreadnought.

Output: 2x2 Contact Sheet Grid (ultra-cinematic, tactile realism, 70mm film aesthetic).

Grid 1: A master technical orthographic blueprint. Fine white and glowing cyan vector lines on a deep obsidian background. Detailed notations in a minimalist Swiss-style font labeling the Piston-Drive Reactor, the Hive-Class Hangar Array, and the Command Monolith. Precise CAD-level complexity.

Grid 2: A 3D volumetric cross-section of the ship. Visible amber fiber-optic networks running through the hull. A massive spherical singularity core pulses at the original hinge location. Tens of thousands of tiny internal deck-lines and micro-machinery suggest a city-scale population.

Grid 3: A massive exterior shot of this utensil inspired ship in deep space. The ship is a brutalist, monolithic slab of dark metal, lit by the harsh, cold white light of a distant star. Deep chiaroscuro shadows. The ship’s surface looks like a practical miniature with heavy texture density, oil stains, and battle scars. Tiny, needle-like escort ships provide a sense of overwhelming scale. Ion-drive exhaust is a subtle, high-intensity white-blue glow.

Grid 4: An ultra-high-end interior shot of the bridge. Focus on three elite Imperial Enforcers standing in a minimalist gallery. Looking into the camera, their armor and weapons they are holding are heavily inspired by the utensil

Style: Tactical realism, shot on 65mm film, Denis Villeneuve brutalism, industrial design by Jony Ive, heavy on physical texture and high-contrast lighting, no digital sheen.

3D Pororo Winter Village Breaking the Fourth Wall

game-asset

A detailed prompt for creating a highly realistic 3D art piece featuring a giant smartphone displaying a miniature Pororo winter village. The scene includes a glowing, jelly-like green ghost character stepping out of the screen and leaning against the bezel, combining warm interior lighting with a cold, bioluminescent forest background for a magical, nostalgic atmosphere.

Show full prompt
Create a highly detailed 3D “breaking the fourth wall” art piece featuring a giant, sleek smartphone standing horizontality.
The phone must display the Ingenious 3D Pororo miniature pororo winter village.hand-drawn orange, salmon, yellow, cream, red, and burgundy Pororo animation, 2 houses and 3 Hanok-style houses on a small hill, three-dimensional snow roofs and shining windows, the main characters in the animation are posing and playing and skating on the ice in a corner, all the contents listed are applied to the phone. Brown, tan, cream-colored thin trees, white snow floor, colorful glittering confetti, contrast between warm interior lighting and cold atmosphere background, boquet effect of falling snowflakes, water droplets in glass, metal lock, painting impressionist style, central composition, magically cozy and nostalgic Christmas atmosphere, dreamy feeling of soft focus.
Green ghost character — a glowing, soft, jelly-like green ghost with a small crown — has stepped out of the phone screen and standing on the ground and , leaning naturally and comfortably against the phone bezel, with rsmiling at the phone screen.
bioluminescent forest ambience, green luminous particles, soft fog, glowing light orbs, dreamy atmosphere.
Use cinematic lighting, photorealistic materials, 8K render detail, crisp subsurface scattering on the ghost character, and realistic reflections on the smartphone.
The composition should feel magical, grounded, and premium.
signature '{argument name="signature" default="Willy"}' is in the bottom-right corner.—ar 4:3
#AIart #prompt #cute #Christmas #pororo #beauty

Photo to Collectible Action Figure Transformation

game-asset

A prompt for transforming an uploaded photo into a highly detailed 3D collectible action figure (1/6 scale), complete with plastic texture, dynamic pose, transparent base, custom blister packaging, and a festive 'Centa Claus' theme.

Show full prompt
Transform this photo into a highly detailed 3D collectible action figure in realistic style, 1/6 scale, posed dynamically on a transparent acrylic round base. Same exact face, outfit, hair, and expression preserved perfectly. Plastic toy texture with subtle gloss and paint details. Include custom packaging box next to it on a shelf background—blister pack with clear window, bold graphics, logo, and original artwork featuring the figure. High-end collectible vibe like Hot Toys or Bandai Tamashii Nations, ultra-realistic lighting, sharp focus, 8K resolution, photorealistic. Add festive theme like Centa Claus edition to add December vibes.

Cartoon to Funko Pop Transformation Prompt

game-asset

A two-part prompt demonstrating the difference between Midjourney and Nano Banana Pro. The Nano Banana Pro prompt focuses on transforming a cartoon concept into a Funko Pop vinyl figure, complete with packaging and specific staging details.

Show full prompt
Transform this cartoon to a Funko Pop vinyl figure. Place the Funko Pop box beside the vinyl figure (side by side) with the name '{argument name="figure name" default="Rainbow Cheese"}' on box. Place vinyl figure and box on a pink surface and pink background with studio lighting.

Minimal Black Ink Illustration Blueprint Prompt

game-asset

A JSON prompt designed to convert an uploaded image into a minimal black ink, full-body illustration style. The output should resemble a moody, artistic drawing created with bold, heavy strokes on plain notebook paper, rendered in 4K resolution.

Show full prompt
{
  "reference_image": "UPLOAD_USER_IMAGE_HERE",
  "subject": {
    "gender": "{argument name="gender" default="male"}",
    "visibility": "full_body"
  },
  "style": {
    "art": "minimal_black_ink_full_body_illustration",
    "medium": "black_pen_on_notebook",
    "linework": "bold_heavy_strokes",
    "mood": "moody_artistic"
  },
  "background": {
    "surface": "plain_notebook_paper"
  },
  "render_settings": {
    "resolution": "4K"
  }
}

Rubberhose 3D Character Prompt

game-asset

A simple, structured prompt for generating a stylized 3D character in the classic rubberhose animation style. It emphasizes a smooth 3D render, dynamic pose, soft lighting, and a solid color background for a modern, playful design.

Show full prompt
[{argument name="subject" default="Subject"}], stylized 3D rubberhose character, smooth 3D render,  Solid {argument name="color" default="Color"} color background, dynamic pose, soft ground shadow, bright soft lighting, modern playful design
Prev 53 / 61 Next

Prompts are model-agnostic and work with Midjourney / DALL-E / Flux / Stable Diffusion.

Information boundary

Information on this page is collected from official documents for technical presentation only and does not imply our endorsement. Pricing, quotas and availability are subject to the latest official statements. We make no commitment regarding any action you take after leaving this site.

Similar skills

视频短视频图片音乐音频配音口播数字人全能创作

Marked paid

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

Marked paid

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。

罗斯蒙德可视化图形生成

Not specified

【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。

AI Image Prompts · 绘画提示词库

Marked free

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

海报设计工作室

FreemiumAPI key required

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,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。

架构图一键生成

Marked paidAPI key required

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。

What is a Skill

A Skill is a packaged single capability, such as text recognition, document summarization, or keyword extraction. Developers wrap the calling logic and prompts into a plugin-like unit, so users can load it without understanding the underlying model. StackPilot indexes a large number of skills that can be tried instantly or assembled into a plan.