JoJoGAN: One Shot Face Stylization

This is the PyTorch implementation of JoJoGAN: One Shot Face Stylization.

Abstract:
While there have been recent advances in few-shot image stylization, these methods fail to capture stylistic details that are obvious to humans. Details such as the shape of the eyes, the boldness of the lines, are especially difficult for a model to learn, especially so under a limited data setting. In this work, we aim to perform one-shot image stylization that gets the details right. Given a reference style image, we approximate paired real data using GAN inversion and finetune a pretrained StyleGAN using that approximate paired data. We then encourage the StyleGAN to generalize so that the learned style can be applied to all other images.

How to use

Everything to get started is in the colab notebook.

Citation

If you use this code or ideas from our paper, please cite our paper:

Acknowledgments

This code borrows from StyleGAN2 by rosalinity, e4e and ReStyle.

Official PyTorch repo for JoJoGAN: One Shot Face Stylization

Related tags

Overview

JoJoGAN: One Shot Face Stylization

How to use

Citation

Acknowledgments

Owner

A variational Bayesian method for similarity learning in non-rigid image registration (CVPR 2022)

Data augmentation for NLP, accepted at EMNLP 2021 Findings

Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

An executor that performs image segmentation on fashion items

CAPITAL: Optimal Subgroup Identification via Constrained Policy Tree Search

Solution to the Weather4cast 2021 challenge

This repository contains the code for: RerrFact model for SciVer shared task

Breaking the Dilemma of Medical Image-to-image Translation

IDA file loader for UF2, created for the DEFCON 29 hardware badge

A Python script that creates subtitles of a given length from text paragraphs that can be easily imported into any Video Editing software such as FinalCut Pro for further adjustments.

Experiments and examples converting Transformers to ONNX

Flexible Networks for Learning Physical Dynamics of Deformable Objects (2021)

An automated algorithm to extract the linear blend skinning (LBS) from a set of example poses

TorchMD-Net provides state-of-the-art graph neural networks and equivariant transformer neural networks potentials for learning molecular potentials

Code for models used in Bashiri et al., "A Flow-based latent state generative model of neural population responses to natural images".

Implementation for "Manga Filling Style Conversion with Screentone Variational Autoencoder" (SIGGRAPH ASIA 2020 issue)

A Dataset for Direct Quotation Extraction and Attribution in News Articles.

Offcial implementation of "A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction, ICCV-2021".

A-ESRGAN aims to provide better super-resolution images by using multi-scale attention U-net discriminators.

A series of Jupyter notebooks with Chinese comment that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.