Documentation

Installation Guide

GlowMatch AI - Makeup Recommendation System Using Face Analysis (Django + MediaPipe Final Year Project)

Step-by-step Setup Verified Instructions Chat Support
Back to Project
Complete Guide

Installation Guide: GlowMatch AI Makeup Recommendation System

This should take about 15 to 20 minutes, even if you've never run a Django project before. Follow the steps in order and don't skip the virtual environment step.

Prerequisites

  • Python 3.10.11 from python.org. Use 3.10, not 3.12 or 3.13, because MediaPipe is the most reliable on 3.10. On Windows, tick "Add Python to PATH" during install.
  • pip, which comes with Python.
  • A webcam if you want live capture. Uploading a photo works without one.
  • Chrome or Edge, which handle webcam permissions the best.
  • A Groq API key (optional), free at console.groq.com. You only need it for AI-written tips.

Step-by-Step Setup

  1. Open the project folder in a terminal. Unzip the project, open the folder in VS Code and open its terminal. On Windows, use Command Prompt rather than PowerShell if activation gives you trouble.

  2. Create and activate a virtual environment.

    python -m venv venv
    venv\Scripts\activate

    On macOS or Linux, run source venv/bin/activate instead. You'll see (venv) at the start of the terminal line when it's active.

  3. Install the dependencies.

    pip install -r requirements.txt

    MediaPipe is a big download, so give it a couple of minutes.

  4. Set up the environment file.

    copy .env.example .env

    On macOS or Linux, use cp .env.example .env. Open .env and paste your GROQ_API_KEY if you have one. If you leave it empty, the app uses offline rule-based tips automatically.

  5. Create the database and load the products.

    python manage.py migrate
    python manage.py seed_products
    python manage.py createsuperuser

    The seed_products command loads the roughly 180-item catalogue. For createsuperuser, pick any username and a password you'll remember. The password won't show while you type, which is normal.

  6. Start the server.

    python manage.py runserver

    Open http://127.0.0.1:8000/ in your browser.

Important URLs

  • /: capture or upload a photo and run the analysis
  • /admin/: manage products, shades, prices and buy links
  • /accounts/signup/: create a user account to save history
  • /history/: view past analyses and compare two of them

Common Issues

  • MediaPipe fails to install. This almost always means you're on the wrong Python version. Check with python --version. If it isn't 3.10, install 3.10.11, delete the venv folder and redo steps 2 and 3.
  • The webcam won't turn on. Allow camera access when the browser asks, and close Zoom, Teams or any other app using the camera. Open the site at 127.0.0.1 or localhost, because browsers block webcams on plain-HTTP IP addresses.
  • "No face detected" on a clear selfie. The face is usually too small, turned sideways, or the room is too dark. Face the camera straight on with your face filling a good part of the frame.

How to Verify It's Working

Upload a front-facing selfie and click analyse. You should see a skin tone (for example, Wheatish), an undertone, a face shape and a list of products. Pick a lipstick and click try-on, and your lips in the photo should change colour without the page reloading. Finally, log in to /admin/ and confirm the Products list has entries. If all three work, you're ready to demo.

Need Help?

Our team is here to assist you with installation and setup.

Chat with Us