alexgenovese / upscaler

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration

  • Public
  • 818.3K runs
  • GitHub
Run with an API
Playground API Examples README Versions

Examples

View more

Run time and cost

This model costs approximately $0.0034 to run on Replicate, or 294 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 5 seconds.

Readme

Upscaler GFPGan

With this endpoint you can increase details and size of any photo with face.

  1. Upload the photo with face(s)
  2. Select the new size and flag if need additional enhancement, that detail the background faces
  3. Generate

Resources - GFPGAN 1.4

Acknowledgements This project is based on GFPGAN you can generate images based on respective licenses and use terms (https://github.com/TencentARC/GFPGAN?tab=License-1-ov-file)

This is a simple implementation of Upscale to generate high-quality and realistic photo shooting in Reica