README.md

FaceEnhance

Enhancing faces in AI generated images.

Installation

Prerequisites

• Python 3.11 or higher
• 1 GPU with 48GB VRAM
• At least 50GB of free disk space

Setup

1. Set up your Hugging Face token:

   • Create a token at Hugging Face
   • Set the following environment variables:

     export HUGGINGFACE_TOKEN=your_token_here
     export HF_HOME=/path/to/your/huggingface_cache
     

   • Models will be downloaded to $HF_HOME and then symlinked to ./ComfyUI/models/
   • Hugging Face requires login for downloading Flux

2. Create the virtual environment:

   python -m venv venv
   source venv/bin/activate
   python -m pip install -r requirements.txt
   

3. Run the install script:

   python install.py
   

This will

• Install ComfyUI, custom nodes, and required dependencies to your venv
• Download all required models (Flux.1-dev, ControlNet, text encoders, PuLID, and more)

Running on ComfyUI

Using the ComfyUI workflows is the fastest way to get started. Run python run_comfy.py

• ./workflows/FaceEnhancementProd.json for face enhancement
• ./workflows/FaceEmbedDist.json for computing the face embed distance

Configuration

Create a .env file in the project root directory with your API keys:

touch .env
echo "FAL_API_KEY=your_fal_api_key_here" >> .env

These API keys are required for certain features of the application to work properly.

Gradio Demo

A simple web interface for the face enhancement workflow.

1. Run

python gradio_demo.py

2. Go to http://localhost:7860. You may need to enable port forwarding.

Notes

• The script and demo run a ComfyUI server ephemerally
• All images are saved in ./ComfyUI/input/scratch/
• Temporary files are created during processing and cleaned up afterward