gans

Image-to-Image Translation in PyTorch

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Bringing Old Photo Back to Life (CVPR 2020 oral)

A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.

The author's officially unofficial PyTorch BigGAN implementation.

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212

A simple interface for editing natural photos with generative neural networks.

A sketch extractor for anime/illustration.

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

Toward Multimodal Image-to-Image Translation

Generative Adversarial Transformers

🏖 Keras Implementation of Painting outside the box

Official PyTorch repo for JoJoGAN: One Shot Face Stylization

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

Synthetic Data Generation for tabular, relational and time series data.

Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks

Generative Adversarial Networks (GANs) resources sorted by citations

Pytorch implementation of MixNMatch

Generative Adversarial Networks implemented in PyTorch and Tensorflow

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

Synthetic structured data generators

Sketch Your Own GAN: Customizing a GAN model with hand-drawn sketches.

AttGAN: Facial Attribute Editing by Only Changing What You Want (IEEE TIP 2019)

[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.

[NeurIPS 2018] Visual Object Networks: Image Generation with Disentangled 3D Representation.

Rewriting a Deep Generative Model, ECCV 2020 (oral). Interactive tool to directly edit the rules of a GAN to synthesize scenes with objects added, removed, or altered. Change StyleGANv2 to make extravagant eyebrows, or horses wearing hats.

A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps