wonjongg / stylecarigan

Caricature Generation via StyleGAN Feature Map Modulation

  • Public
  • 5.4K runs
  • T4
  • GitHub
  • Paper
  • License
Iterate in playground

Input

image
*file

Input image, only supports images with .png and .jpg extensions

string

Output a png file with num_samples in a grid, or a zip file with all 64 samples

Default: "png"

integer

Valid when output_type is png. Choose number of samples to view in a grid

Default: 1

Output

file

This output was created using a different version of the model, wonjongg/stylecarigan:8b4fe870.

Run time and cost

This model costs approximately $0.13 to run on Replicate, or 7 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 T4 GPU hardware. Predictions typically complete within 10 minutes. The predict time for this model varies significantly based on the inputs.

Readme

StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation

This repository contains the official PyTorch implementation of the following paper:

StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation
Wonjong Jang, Gwangjin Ju, Yucheol Jung, Jiaolong Yang, Xin Tong, Seungyong Lee, SIGGRAPH 2021

It inverts latent codes from input photos and generates caricatures from latent codes.

Citation

If you find this code useful, please consider citing:

@article{Jang2021StyleCari,
  author    = {Wonjong Jang and Gwangjin Ju and Yucheol Jung and Jiaolong Yang and Xin Tong and Seungyong Lee},
  title     = {StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation},
  booktitle = {ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH)},
  publisher = {ACM},
  volume = {40},
  number = {4},
  year = {2021}
}

Contact

You can have contact with wonjong@postech.ac.kr or ycjung@postech.ac.kr