← 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License information is collected from official sources and may be outdated or missing.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.

224 matches

Cinematic Venom Symbiote Action Scene

youtube-thumbnail

A prompt for generating an ultra-realistic cinematic movie scene featuring a young man (with identity locked to a reference photo) in a dynamic action pose, with a Venom-like symbiote bursting from his back. The prompt specifies the setting (dark industrial warehouse), lighting (sharp light beams, warm highlights), and camera angle (low and tilted) for a Hollywood action-poster vibe.

Show full prompt
16K ultra-realistic cinematic movie scene of the same young man (keep his real facial features and proportions exactly as in the reference photo, no changes to his face). He is in a dynamic action pose, slightly crouched forward as if ready to leap or attack, one knee bent, one hand pressing firmly on the ground, the other reaching out with intense motion. From his back, a Venom-like symbiote bursts outward, forming huge menacing tendrils and a snarling monstrous face rising above his shoulder. The dark industrial warehouse setting is filled with mist and drifting smoke, with sharp light beams slicing through the fog. Camera angle is low and slightly tilted for dramatic tension and high-energy impact. Add warm highlights, motion blur, lens flares, and subtle film-grain for a Hollywood action-poster vibe. Generate the face using the uploaded reference image with accurate likeness.

Cinematic 3D Action Advertisement Prompt

youtube-thumbnail

A prompt for generating a cinematic, action-packed 3D advertisement. It emphasizes dramatic studio lighting, dynamic particle effects, high-impact slow-motion energy, and ultra-hyperrealistic rendering, with instructions to seamlessly integrate the brand logo and a modern slogan.

Show full prompt
Cinematic 3D action-packed advertisement for {argument name="product brand" default="[INSERT PRODUCT/BRAND HERE]"}, captured in an intense mid-motion moment with dramatic studio lighting, dynamic particle effects, and high-impact slow-motion energy. Ultra-hyperrealistic rendering, razor-sharp details, glossy commercial finish, atmospheric depth, and powerful contrast. Viral-ready composition with the brand logo seamlessly integrated into the scene and a sleek, modern slogan positioned cleanly beneath. High-end blockbuster commercial aesthetic

Kling 3.0 video using Nano Banana Pro images

youtube-thumbnail

A video created using Kling 3.0 Omni, which sequences four images generated by Nano Banana Pro based on a shared prompt (developed by GPT-5). The prompt focuses on a cinematic, four-cut sequence depicting a woman's charm through casual conversation, using ASMR and binaural audio.

Show full prompt
A cinematic video composed of 4 cuts, depicting a woman's charm through casual conversation with friends. Seamlessly connect a medium shot of a smile, ASMR sounds of hands, a close-up of a whisper, and a lingering pull-back shot. Combine film-like texture and binaural audio to enhance immersion from both visual and auditory perspectives.

Detailed Japanese Prompt for Variety Show Style Image

youtube-thumbnail

A highly detailed, multi-section prompt written entirely in Japanese for generating an image in the style of a TV variety show, focusing on a funny cat mishap. The prompt specifies text content, color schemes (using hex codes), fonts (variety show style, friendly rounded text), layout, subject (cat failing a jump, making a funny face), and overall style (comedy, decisive moment, smartphone photo look).

Show full prompt
Please output 4 times using the following prompt:

Text
Main: {argument name="main text" default="Miracle at Broadcast Accident Level"}
Sub: {argument name="sub text" default="Funny Cat Mishap Collection"} (bottom banner)
Other: Why did that happen w (speech bubble), Decisive Moment (top right stamp)

Color Scheme
Background: General living room (with signs of life, no specific brand furniture).
Text: Pop colors like #FFA500 (orange) and #FFFF00 (yellow).
Accent: Colors for comic-style concentration lines.

Font
Main: Fun, extra-bold font typical of variety shows.
Sub: Friendly, rounded text.

Layout
Text Placement:
Large main title at the top. Add movement to the text (italics, curve).
Place 'w' or speech bubbles near the cat's face.
Decoration/Figures:
Main subject is a cat (or dog).
Moments like failing a jump and being in a strange posture, funny faces, or flipping things over.
Motion blur to emphasize movement (subject blur) and comic sound effect effects (Don!, Biyooon, etc.).
Show the messy room without hiding it.

Style
Pet video, mishap, comedy, decisive moment, sense of dynamism, friendly, smartphone photo style

Historical Social Media Feed Generation

youtube-thumbnail

A prompt testing Nano Banana 2's ability to research historical events from a specific date (December 9, 1971), find images of the key figures, and generate a vertical format image simulating an X (Twitter) feed where those figures post in Spanish on that day.

Show full prompt
I was born on December 9, 1971. Investigate what happened in the world that day, search for images of the protagonists of those news stories, and create an image of an X (Twitter) feed as if those characters had posted that day. Vertical format, all writing in Spanish.

Cinematic 4-Cut Video Prompt of Woman Painting

youtube-thumbnail

A cinematic video prompt, generated by GPT-5 and used for Kling 3.0 Omni, describing a four-cut sequence of a cute woman painting a wall. The prompt specifies camera shots (extreme close-up, medium, artistic cut, wide shot), soft pastel tones, and shallow depth of field to create a warm atmosphere.

Show full prompt
A cinematic video composed of four cuts, themed around a cute woman painting a wall. Smoothly transitioning to an extreme close-up of scooping paint onto a brush, a medium shot of her happily painting the wall, an artistic cut capturing dripping paint, and a wide shot of her smiling contentedly in front of the finished wall. The overall look uses soft pastel tones and shallow depth of field to create a unified, warm atmosphere.

Interstellar-Inspired Cinematic Film Stills Prompt

youtube-thumbnail

A simple prompt requesting the generation of cinematic, ultra-realistic film stills inspired by the movie Interstellar, emphasizing consistent color grading and outputting an aesthetic storyboard.

Show full prompt
Create cinematic, ultra-realistic film stills inspired by Interstellar (Christopher Nolan vibe).
Look like real movie screenshots with consistent color grading, 
Output as an aesthetic storyboard:  visually cohesive, no text

Spy Thriller Comedy Storyboard Prompt

youtube-thumbnail

A narrative prompt designed to generate a multi-panel storyboard for a comedic spy thriller scene involving tactical agents staking out a suburban dad who is just looking for milk in his fridge.

Show full prompt
Early morning. Total silence.

A hyper-serious spy thriller vibe.

A sleek black SUV idles outside a quiet suburban house. Two “tactical” men in earpieces whisper intensely.

“Target is inside.”
“Movement in the kitchen.”
“Stand by.”
Inside the house—
A dad in sweatpants stands in front of the fridge, staring into it like it contains classified secrets.

Cut back outside.

“Subject has opened the cold storage unit.”
“Thermal spike detected.”

Inside, he pulls out milk. Shakes it. Sniffs it. Makes a face.

Outside, one agent squints at a tablet.
“He’s analyzing chemical integrity.”
The front door creaks open.

The dad steps onto the porch in mismatched slippers to grab the newspaper.

Both agents snap alert.
“Target exiting the compound.”
“Visual confirmed. He looks… unstable.”
The dad waves awkwardly at them.

They freeze.

He squints. “You guys DoorDash?”

Beat.
They look at each other.
Inside the SUV, a third “commander” barks through the radio:
“Abort. Wrong house. Again.”

The agents slowly lower their sunglasses.

The dad shrugs, walks back inside.

Cut to kitchen.

He sits at the table with his cereal. Turns on the TV.

BREAKING NEWS: “International spy ring apprehended after staking out random suburban dad for third straight day.”

He crunches loudly.
Milk drips down his chin.

He sighs.

“Finally.”

Epic Fantasy Warriors: Fire and Ice Cinematic Poster

youtube-thumbnail

A prompt for generating a dramatic, cinematic poster-style portrait of two epic fantasy warriors standing back-to-back in a frozen storm, symbolizing the clash of fire and ice with specific details on their appearance, attire, and the contrasting lighting and atmosphere.

Show full prompt
A dramatic cinematic poster-style portrait of two epic fantasy warriors standing back-to-back in a frozen storm. On the left, a battle-worn male warrior with wet, curly dark hair, head bowed in quiet resolve, gripping a medieval sword planted into the ice. Frost and snow cling to his fur-lined cloak and shoulders. On the right, a powerful female warrior in profile, pale skin glowing with fiery orange light, her body partially engulfed in flames thatcontrast against the icy blue atmosphere. Snow particles swirl through the air, blending fire and ice in a symbolic clash. Ultra-detailed faces, emotional intensity, volumetric fog, cinematic lighting, cold blue tones mixed with warm fire highlights, shallow depth of field, epic fantasy movie poster, hyper-realistic, 8K resolution, dramatic composition, sharp focus, high contrast, photorealistic textures.

Double Exposure Portrait of an AI Engineer

youtube-thumbnail

A prompt for generating a hyper-realistic, double exposure photograph combining the silhouette of an AI engineer's profile with a symbolic environment of glowing neural networks and futuristic server architecture, suitable for a stock photo aesthetic.

Show full prompt
A double exposure photograph depicting the silhouette profile and headshot portrait of an AI engineer, with a symbolic environment constructed from glowing neural networks, floating code streams, and futuristic server architecture, in the style of double exposure photography, sun flare, white background, hyper-realistic, detailed rendering, stock photo, high-resolution photography.

Cinematic Futuristic Portrait Prompt

youtube-thumbnail

A prompt for generating a cinematic, high-contrast futuristic portrait of a person in streetwear, seated on a neon-green glowing Spotify stool, set in a dark digital studio with holographic elements.

Show full prompt
Cinematic futuristic portrait of a person in casual streetwear and headphones, seated on a neon-green glowing stool with Spotify emblem. Dark digital studio with holographic sound waves, floating notes, and playlist UI panels. Dramatic neon rim lighting, volumetric fog, ultra-realistic, high contrast, shallow depth of field, 35mm lens, 8K, immersive musical vibe --ar 16:9.

Cyber Projector Numbers Beauty Portrait Prompt (JSON format)

youtube-thumbnail

A highly detailed JSON-formatted Nano Banana Pro prompt for generating an ultra-high resolution, cinematic beauty portrait of a woman with green numeric projections mapped across her face and body, emphasizing photorealism, low-key lighting, and correct projection physics.

Show full prompt
{
  "generation_request": {
    "meta_data": {
      "tool": "NanoBanana Pro",
      "task_type": "cyber_projector_numbers_beauty_portrait",
      "version": "v1.0_GREEN_NUMBERS_PROJECTION_BEAUTY",
      "priority": "highest",
      "language": "en"
    },
    "input": {
      "mode": "text_to_image",
      "notes": "Create a photoreal cinematic beauty portrait of an adult woman with green numeric projections mapped across her face, neck, shoulders, and chest. The projection must look physically correct (wraps around facial contours), with soft falloff and slight blur at edges. Dark background with faint out-of-focus green digits. Moody, low-key lighting. No text, no watermark."
    },
    "output_settings": {
      "aspect_ratio": "4:5",
      "orientation": "portrait",
      "resolution_target": "ultra_high_res",
      "num_images": 1,
      "render_style": "cinematic_techno_editorial",
      "sharpness": "filmic_crisp",
      "grain": "subtle_35mm",
      "color_grading": "green_on_black_low_key"
    },
    "scene": {
      "environment": "dark studio, faint bokeh of green digits in the background",
      "lighting": "primary light is the projector (green digits), minimal soft fill from camera-left, deep shadows",
      "mood": "mysterious, cyber, intimate"
    },
    "subject": {
      "person": "adult woman",
      "pose": "3/4 portrait, head slightly tilted, eyes looking sideways past camera",
      "expression": "calm, intense, enigmatic",
      "hair": "long dark hair, sleek and natural",
      "makeup": "clean editorial skin, subtle shimmer on eyelids, soft liner, natural glossy lips",
      "skin_texture": "natural pores, realistic highlights"
    },
    "camera": {
      "camera_body": "ARRI Alexa Mini",
      "lens": "85mm prime",
      "aperture": "f/2.0",
      "focus": "sharp on eyes and lips, projection still readable, background bokeh"
    },
    "projection_details": {
      "content": "random green digits (0-9) and simple symbols",
      "behavior": "wraps on cheekbones, nose bridge, jawline, collarbones",
      "quality": "slight projector softness, realistic spill light on skin"
    },
    "negative_prompt": "text, watermark, logo, letters, neon signs, cartoon, anime, CGI look, plastic skin, over-smoothing, distorted face, extra limbs, extra fingers, deformed hands, incorrect projection physics, flat overlay, low resolution, heavy HDR"
  }
}
Prev 5 / 19 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。

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。

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。

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

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.