An interactive web application for real-time drone assembly assistance using advanced AI technologies.

Drone Assembler helps users build drones by providing real-time component identification, step-by-step assembly instructions, and visual validation. The application leverages Google's Gemini AI for component recognition and the Janus-1.3B model for generating visual drone representations.

• Real-time Component Identification: Identifies drone parts using your device camera
• Step-by-step Assembly Instructions: Guided assembly process with visual references
• Assembly Validation: Real-time validation to ensure correct component placement
• Voice Control: Hands-free operation with voice command support
• Project Management: Save and manage multiple drone assembly projects
• Drone Visualization: Generate realistic drone images using the Janus-1.3B model

Used for real-time component recognition, assembly validation, and instruction generation.

A specialized image generation model that creates realistic drone visualizations based on component selection and assembly configuration. The Janus model enables:

• Photorealistic drone renders
• Multiple angles and perspectives
• Component-accurate visualizations
• Custom color schemes and designs

• React.js
• TailwindCSS
• Supabase Client

• Node.js with Express
• Google Generative AI (Gemini)
• Winston logger
• Supabase integration

• Python with Flask
• Janus-1.3B model
• PyTorch & Transformers

The application consists of three main components:

1. Frontend Application: React-based UI with camera integration and real-time feedback
2. Backend API Server: Express server handling AI processing and database operations
3. Image Generation Service: Python service for Janus model integration

• Node.js (v16+)
• Python 3.9+
• Supabase account
• Google Gemini API key

1. Clone the repository

   git clone https://github.com/yourusername/drone_assembler.git
   cd drone_assembler
   

2. Set up the backend

   cd backend
   npm install
   

   Create a .env file with:

   PORT=5003
   GEMINI_API_KEY=your_gemini_api_key
   SUPABASE_URL=your_supabase_url
   SUPABASE_KEY=your_supabase_key
   

3. Set up the frontend

   cd ../frontend
   npm install
   

   Create a .env file with:

   REACT_APP_SUPABASE_URL=your_supabase_url
   REACT_APP_SUPABASE_ANON_KEY=your_supabase_key
   REACT_APP_API_URL=http://localhost:5003
   

4. Set up the image generation service

   cd ../services
   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   pip install -r requirements.txt
   

1. Start the backend

   cd backend
   npm start
   

2. Start the frontend

   cd frontend
   npm start
   

3. Start the image generation service

   cd services
   ./start_service.sh  # On Windows: start_service.bat
   

• /api/assembly/gemini/validate - Validate assembly progress
• /api/assembly/gemini/instructions - Get assembly instructions
• /api/assembly/gemini/identify-parts - Identify components
• /api/assembly/project - Project management
• /api/assembly/visualize - Generate visualizations

• /generate - Generate drone images
• /progress/:taskId - Check generation progress
• /result/:taskId - Retrieve generated images

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License - see the LICENSE file for details.

• Google Gemini
• Janus Model
• Supabase
• React