SkinRashGenerator is a deep learning project that generates synthetic images of skin rashes based on textual descriptions. This project utilizes fine-tuned CLIP models integrated with latent diffusion techniques to create images that vary by rash type, skin color, and affected area.
- Customizable Rash Generation: Generate images of common skin rashes with customization options for type of rash, skin tone, and body area.
- High-Fidelity Images: Produce realistic and detailed images of skin rashes for educational and diagnostic purposes.
- Web Deployment: Deploy the application using Streamlit for a user-friendly web interface.
- Alternative Deployment: Option to deploy the application using Flask and React for a more traditional web application.
These instructions will help you set up the project on your local machine for development and testing purposes.
- Prerequisites
- Python
- PyTorch
- Streamlit (for web deployment)
- Flask and React (for alternative deployment)
- Git clone the repository:
git clone https://github.com/deveshcode/SkinRashGenerator.git
cd shopping-multimodal-rag
- Install the required packages:
pip install -r requirements.txt
- Create a .env file in the root directory and add your API keys:
OPENAI_API_KEY=your_open_ai_key
Generate images by typing commands such as:
- "Generate a ringworm rash on fair skin at the neck area."
- "Show eczema on brown skin on the hand."
To run the Streamlit app:
streamlit run app.py
To run the Python app:
python app.py
Open the provided URL in your web browser to access the application.
Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
Distributed under the MIT License. See LICENSE for more information.