Banatie - Nano Banana Image Generation Service

A REST API service for AI-powered image generation using the Gemini Flash Image model. Banatie provides a simple HTTP interface for generating high-quality images from text prompts with optional reference images.

🚀 Quick Start

Prerequisites

• Node.js >= 18.0.0
• pnpm >= 8.0.0
• Gemini API key from Google AI Studio

Installation

# Clone the repository
git clone <repository-url>
cd banatie

# Install dependencies
pnpm install

# Setup environment variables
cp .env.example .env
# Edit .env with your Gemini API key

Development

# Start development server with auto-reload
pnpm dev

# Start production server
pnpm start

# Build for production
pnpm build

📝 Environment Configuration

Copy .env.example to .env and configure:

# Required
GEMINI_API_KEY=your_gemini_api_key_here

# Optional (with defaults)
PORT=3000
NODE_ENV=development
CORS_ORIGIN=*
MAX_FILE_SIZE=5242880  # 5MB
MAX_FILES=3
RESULTS_DIR=./results
UPLOADS_DIR=./uploads/temp
LOG_LEVEL=info

🔌 API Endpoints

Health Check

GET /health

Returns server status and uptime.

API Information

GET /api/info

Returns API details and configuration.

Generate Image

POST /api/generate
Content-Type: multipart/form-data

Parameters:

• prompt (string, required): Text description for image generation
• filename (string, optional): Custom filename for the generated image
• referenceImages (files, optional): Up to 3 reference images (5MB max each)

Supported formats: PNG, JPEG, JPG, WebP

📖 Usage Examples

cURL

# Basic text-to-image
curl -X POST http://localhost:3000/api/generate \
  -F "prompt=A magical forest with glowing mushrooms" \
  -F "filename=magical_forest"

# With reference images
curl -X POST http://localhost:3000/api/generate \
  -F "prompt=Character in medieval armor like the reference" \
  -F "referenceImages=@./reference.jpg"

JavaScript/Fetch

const formData = new FormData();
formData.append('prompt', 'A futuristic cityscape at sunset');
formData.append('filename', 'futuristic_city');

const response = await fetch('http://localhost:3000/api/generate', {
  method: 'POST',
  body: formData
});

const result = await response.json();
console.log(result);

Response Format

{
  "success": true,
  "message": "Image generated successfully",
  "data": {
    "filename": "generated_image_123.png",
    "filepath": "./results/generated_image_123.png",
    "description": "Generated image description",
    "model": "gemini-2.0-flash-exp",
    "generatedAt": "2024-01-01T12:00:00.000Z"
  }
}

🛠️ Development Scripts

# Development
pnpm dev              # Start with auto-reload
pnpm build            # Build for production
pnpm start            # Start production server

# Code Quality
pnpm typecheck        # TypeScript type checking
pnpm lint             # ESLint code linting
pnpm lint:fix         # Fix ESLint issues
pnpm format           # Format code with Prettier
pnpm format:check     # Check code formatting

# Testing
pnpm test             # Run tests
pnpm test:watch       # Run tests in watch mode
pnpm test:coverage    # Run tests with coverage

🏗️ Project Structure

banatie/
├── src/
│   ├── middleware/          # Express middleware
│   ├── routes/             # API route handlers
│   ├── services/           # Business logic services
│   ├── types/              # TypeScript type definitions
│   ├── utils/              # Utility functions
│   ├── app.ts              # Express app configuration
│   └── server.ts           # Server entry point
├── tests/                  # Test files
├── results/                # Generated images output
├── uploads/                # Temporary file uploads
└── logs/                   # Application logs

🔧 Configuration

File Limits

• Max file size: 5MB per image (configurable)
• Max files: 3 reference images per request (configurable)
• Request size: 10MB total request limit

Supported Image Formats

• PNG
• JPEG/JPG
• WebP

🚦 Error Handling

The API provides detailed error responses:

Validation Errors (400):

• Missing required parameters
• Invalid file formats
• File size exceeded
• Too many files

Server Errors (500):

• Missing API key configuration
• Image generation failures
• Internal processing errors

📄 License

MIT License - see LICENSE file for details.

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Run tests and linting
5. Submit a pull request

📞 Support

For issues and questions, please open an issue on the GitHub repository.