Llama Image Captioner

An elegant Python application that generates detailed image captions using Meta's Llama 3.2 90B Vision model through the OpenRouter API.

Features

• 🖼️ Simple drag-and-drop image upload interface
• 🔄 Choose between short and detailed captions
• 🤖 Powered by Meta-Llama 3.2 90B Vision Instruct model
• 🌐 Easy-to-use Gradio web interface
• ⚡ Fast and accurate image analysis

Prerequisites

• Python 3.7 or higher
• OpenRouter API key (get it from OpenRouter)
• Internet connection

Installation

1. Clone the Repository

git clone https://github.com/PierrunoYT/llama-image-captioner.git
cd llama-image-captioner

2. Set Up Python Environment

Choose your operating system:

Windows

# Create a virtual environment
python -m venv venv

# Activate the environment
venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

macOS/Linux

# Create a virtual environment
python3 -m venv venv

# Activate the environment
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

3. Configure API Keys

You can set up your environment variables in two ways:

Option 1: Using .env file (Recommended)

1. Copy the example environment file:

   cp .env.example .env

2. Edit the .env file and replace the values with your actual configuration:

   OPENROUTER_API_KEY=your_api_key_here
   YOUR_SITE_URL=http://localhost:7860
   YOUR_APP_NAME=Llama Image Captioner
   

Option 2: Using System Environment Variables

Windows (Command Prompt)

setx OPENROUTER_API_KEY "your_api_key_here"
setx YOUR_SITE_URL "http://localhost:7860"
setx YOUR_APP_NAME "Llama Image Captioner"

Windows (PowerShell)

[System.Environment]::SetEnvironmentVariable('OPENROUTER_API_KEY', 'your_api_key_here', 'User')
[System.Environment]::SetEnvironmentVariable('YOUR_SITE_URL', 'http://localhost:7860', 'User')
[System.Environment]::SetEnvironmentVariable('YOUR_APP_NAME', 'Llama Image Captioner', 'User')

macOS/Linux

Add these lines to your ~/.bashrc, ~/.zshrc, or equivalent:

export OPENROUTER_API_KEY="your_api_key_here"
export YOUR_SITE_URL="http://localhost:7860"
export YOUR_APP_NAME="Llama Image Captioner"

Then reload your shell configuration:

source ~/.bashrc  # or source ~/.zshrc

Running the Application

1. Make sure your virtual environment is activated:

   • Windows: venv\Scripts\activate
   • macOS/Linux: source venv/bin/activate

2. Start the application:

python ImageCaption.py

3. Open your web browser and navigate to:
   • Local URL: http://localhost:7860
   • The interface will open automatically in your default browser

Usage

1. Upload an image using one of these methods:

   • Drag and drop an image into the upload area
   • Click the upload area to select an image from your files
   • Paste an image from your clipboard

2. Select caption length:

   • Short: Brief, concise description
   • Long: Detailed analysis of the image

3. Click "Submit" and wait for the caption to be generated

Troubleshooting

Common Issues

1. API Key Error

   • Ensure you've set the environment variables correctly
   • Restart your terminal/command prompt after setting environment variables
   • Check if your API key is valid

2. Import Errors

   • Verify that your virtual environment is activated
   • Reinstall dependencies: pip install -r requirements.txt

3. Connection Issues

   • Check your internet connection
   • Verify that OpenRouter API is accessible from your network

Contributing

1. Fork the repository
2. Create your feature branch: git checkout -b feature/AmazingFeature
3. Commit your changes: git commit -m 'Add some AmazingFeature'
4. Push to the branch: git push origin feature/AmazingFeature
5. Open a Pull Request

License

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

Copyright (c) 2025 PierrunoYT

Links

• GitHub Repository
• OpenRouter API
• Gradio Documentation