Image Enhancer

High-resolution image enhancement powered by AI.

Before / After Example

Before	After

Description

This application provides a simple web interface to enhance images using an AI upscaling model. Upload your low-resolution images and get high-resolution results.

Features

Web UI for easy image uploading and enhancement.
API endpoint for programmatic access (/enhance).
Selectable upscaling models and scale factors.
Optional face enhancement.
Input and output images are saved in api_inputs and api_outputs respectively.

Installation

Clone the repository:

git clone https://huggingface.co/sayed99/Image-Enhancer
cd Image-Enhancer

Create Conda Environment: Set up the necessary environment using the provided environment.yml file:
```
conda env create -f environment.yml
conda activate esrgan-env
```
(Note: The environment name is defined within the environment.yml file)
Download Model Weights: The required model weights (.pth files) need to be placed in the Real-ESRGAN/weights/ directory. Common models include:
- RealESRGAN_x4plus.pth
- RealESRGAN_x2plus.pth You can usually find these linked from the original Real-ESRGAN repository or other model sources.

Usage

Run the application using the provided script:

python run.py

This will:

Start the backend API server (usually on http://localhost:8000).
Start the Streamlit web interface (usually on http://localhost:8501).
Open the web interface in your default browser.

Navigate to the web interface, upload an image, select your desired options (model, scale, face enhancement), and click "Enhance Image".

API Usage

You can also interact with the API directly.

Enhance Endpoint: POST /enhance/

Form Data:

file: The image file to upload.
model_name (optional, default: RealESRGAN_x4plus): Model to use (e.g., RealESRGAN_x4plus, RealESRGAN_x2plus).
outscale (optional, default: 4.0): The desired output scale factor (e.g., 2.0, 4.0).
face_enhance (optional, default: false): Boolean flag to enable face enhancement.
fp32 (optional, default: false): Boolean flag to use FP32 precision.

Example using curl:

curl -X POST "http://localhost:8000/enhance/" \
     -F "file=@/path/to/your/image.jpg" \
     -F "model_name=RealESRGAN_x4plus" \
     -F "outscale=4.0" \
     -o enhanced_image.jpg

Notes

Ensure the API server is running before using the Streamlit app or sending direct API requests.
The application uses significant resources (RAM, potentially GPU if configured).
Input images are saved in the api_inputs directory.
Output images are saved in subdirectories within the api_outputs directory, named by a unique request ID.