ComicAI
🎨 AI-powered comics & animated videos using Google’s Gemini, Imagen & Veo 3. Create humorous, educational, or inspirational stories through a simple web interface.
Install / Use
npx skills add vaibhav-malpani/ComicAIInstalls into whichever agent you are using.
README
Comics Generator
A full-stack web application that automatically generates comic strips using Google's Gemini AI for storytelling and Imagen for visual creation. Transform any topic into engaging visual comics with customizable tones and styles through an intuitive web interface.
Examples
Explore the incredible range of comics you can create with ComicsAI! From educational content to hilarious adventures, each example showcases different tones, audiences, and creative possibilities.
🤣 Humorous Comics
"The Great Halloween Pie Heist"
Tone: Humorous | Audience: Kids

Join two bumbling detectives as they investigate the most delicious crime of the century - someone has stolen all the Halloween pies! Watch as our heroic duo follows candy wrapper clues, interviews costumed suspects, and uses their "expert" detective skills to solve this spooky-silly mystery. With plenty of Halloween hijinks and laugh-out-loud moments, this comic proves that sometimes the best mysteries are the sweetest ones to solve!
📚 Educational Comics
"How Astronauts Live on the International Space Station"
Tone: Educational | Audience: General

Transform complex space science into digestible visual learning! This educational comic breaks down life in zero gravity, showing daily routines, eating habits, and scientific work aboard the ISS. Perfect for classrooms or curious minds of all ages.
🌟 Inspirational Comics
"Seasonal Migration Patterns of Birds"
Tone: Inspirational | Audience: General

Nature's most incredible journey told through inspiring visuals! This comic transforms scientific facts about bird migration into an uplifting story about perseverance, navigation, and the wonders of the natural world.
🎬 Video Generation Comics
"The Journey to Discover One's Power" - The Unfolding Bloom
Tone: Inspirational | Audience: General | 🆕 Now with Video!
Click the image above to download and watch the video (MP4 format)
Experience the power of AI-generated video storytelling! This groundbreaking example showcases our new video generation feature, transforming a static comic about self-discovery into a dynamic, animated experience. Watch as Elara discovers her inner power through beautifully animated panels that bring the story to life with smooth transitions, character consistency, and cinematic flow.
Video Features Demonstrated:
- 🎭 Character Consistency: Elara maintains her appearance across all animated panels
- ⚡ Dynamic Animation: Static panels transform into flowing video sequences
- 🎬 Cinematic Composition: Professional video editing with seamless panel transitions
- ⏱️ Processing Metrics: Generated in ~7 minutes (68s comic + 402s video)
- ☁️ Cloud Integration: Seamlessly managed through Google Cloud Storage
💡 What Makes These Examples Special?
🎯 Diverse Topics
From robotics to space exploration, cosmic entities to environmental heroes - these examples showcase the unlimited creative potential of your imagination combined with AI.
🎭 Tone Mastery
Each comic perfectly captures its intended tone:
- Humorous: Light-hearted, accessible, and entertaining
- Educational: Informative yet engaging, perfect for learning
- Inspirational: Uplifting and motivational storytelling
🎨 Visual Excellence
Notice how each comic features:
- Consistent art style throughout panels
- Clear, readable dialogue integrated seamlessly
- Expressive characters that convey emotion
- Dynamic compositions that guide the reader's eye
📖 Story Structure
Every example demonstrates solid comic storytelling:
- Setup: Introducing characters and concepts
- Development: Building the narrative or educational content
- Payoff: Satisfying conclusion with humor, learning, or inspiration
🚀 Try These Prompts Next!
Inspired by these examples? Here are some prompt ideas to get you started:
Educational Series
- "How photosynthesis works, explained by talking trees"
- "The journey of a plastic bottle through recycling"
- "Ancient Roman engineering marvels in modern times"
Humorous Adventures
- "A vampire trying to use modern dating apps"
- "Office supplies come to life during a late-night work session"
- "A time traveler gets confused by modern technology"
Inspirational Stories
- "A young artist overcoming creative block"
- "The story of how small actions can change the world"
- "Learning to embrace failure as a stepping stone to success"
🎪 Mix and Match
The real magic happens when you experiment with different combinations:
- Educational + Humorous: "Quantum physics explained by confused cats"
- Inspirational + Technical: "A coding bootcamp graduate's journey to their first job"
- Dramatic + Educational: "The race to develop vaccines during a pandemic"
Remember: every example started with a simple idea and a click of the "Generate Comic" button. Your next masterpiece is just a prompt away!
🚀 Tech Stack
Backend
- Python 3.11+ - Core programming language
- FastAPI - Modern async web framework and REST API
- Uvicorn - ASGI server for FastAPI
- Google Gemini AI - Story and dialogue generation
- Google Imagen - Comic artwork generation
- Google Veo 3 - AI-powered video generation from comic panels
- OpenCV & Pillow - Image processing and video composition
- Google Cloud Storage - Dynamic bucket management for video assets
- asyncio - Asynchronous processing for better performance
Frontend
- React 18.2.0 - Modern UI framework
- Vite 5.0.0 - Fast build tool and dev server
- Tailwind CSS 3.3.6 - Utility-first styling
- React Query - Server state management
- React Router - Client-side routing
- Axios - HTTP client for API calls
- React Hot Toast - User notifications
- Lucide React - Icon library
📋 Prerequisites
Before getting started, make sure you have:
- Python 3.11 or higher installed on your system
- FFmpeg - Required for video processing and generation
- Windows: Download from ffmpeg.org or install via Chocolatey:
choco install ffmpeg - macOS: Install via Homebrew:
brew install ffmpeg - Linux (Ubuntu/Debian):
sudo apt update && sudo apt install ffmpeg - Linux (CentOS/RHEL):
sudo yum install ffmpegorsudo dnf install ffmpeg
- Windows: Download from ffmpeg.org or install via Chocolatey:
- Google Cloud Project with billing enabled
- Google Cloud credentials with access to:
- Gemini API
- Vertex AI (for Imagen)
- Veo 3 API (for video generation)
- Google Cloud Storage (for video asset management)
- Git for cloning the repository
🛠️ Installation
Backend Setup
-
Clone the repository:
git clone <repository-url> cd ComicAI -
Set up Python virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install Python dependencies:
pip install -r requirements.txt
Frontend Setup
-
Navigate to frontend directory:
cd frontend -
Install Node.js dependencies:
npm install -
Return to project root:
cd ..
⚙️ Configuration
-
Create environment file:
cp .env.example .env -
Configure your API credentials in
.env:# Gemini API Configuration GEMINI_API_KEY=your_gemini_api_key_here # Google Cloud Project Configuration GOOGLE_CLOUD_PROJECT=your_google_cloud_project_id # Storage Configuration (Optional) GCS_BUCKET_NAME=your_custom_bucket_name # Auto-generated if not specified # Optional: Logging level LOG_LEVEL=INFO -
Get your API keys:
- Gemini API Key: Visit Google AI Studio
- Google Cloud Project: Create a project at Google Cloud Console
-
Set up Google Cloud authentication:
gcloud auth application-default login
💰 API Costs & Quotas
Important: Video generation uses Google's premium AI services. Be aware of costs:
⚠️ Pricing Disclaimer: The costs and quotas mentioned below are estimates and may change frequently. For the most current and accurate pricing information, always refer to the official Google Cloud Pricing page and your specific service documentation:
Estimated Costs Per Generation
- Comic Generation: ~$0.10-0.30 per comic (Gemini + Imagen)
- Video Generation: ~$2.00-8.00 per video (Veo 3 pricing varies by duration/quality)
- Storage: ~$0.02-0.10 per GB/month (Google Cloud Storage)
Quota Considerations
- Veo 3: Limited requests
Related Skills
qqbot-channel
385.5kQQ channel management skill. Use qqbot_channel_api for explicit QQ channel-management requests; confirm write, delete, and bulk actions before calling authenticated QQ Open Platform endpoints.
agent-tui
106.4kMain Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection
async-pr-review
106.4kTrigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.
ci
106.4kA specialized skill for Gemini CLI that provides high-performance, fail-fast monitoring of GitHub Actions workflows and automated local verification of CI failures. It handles run discovery automatically—simply provide the branch name.

