The is the source code for a RunPod Serverless worker that uses Real-ESRGAN for Restoration/Upscaling.

The following models are available by default:

• RealESRGAN_x2plus
• RealESRGAN_x4plus
• RealESRNet_x4plus
• RealESRGAN_x4plus_anime_6B

1. Local Testing
2. RunPod Testing

1. Building the Image

The worker provides an API for inference. The API payload looks like this:

{
  "input": {
     "source_image": "base64 encoded source image content",
     "model": "RealESRGAN_x4plus",
     "scale": 2,
     "face_enhance": true
  }
}

The serverless handler (handler.py) is a Python script that handles inference requests. It defines a function handler(event) that takes an inference request, runs the inference using the Real-ESRGAN model, and returns the output as a JSON response in the following format:

{
  "output": {
    "status": "ok",
    "image": "base64 encoded output image"
  }
}

• Real-ESRGAN (ai-forever)

Pull requests and issues on GitHub are welcome. Bug fixes and new features are encouraged.