Repository navigation
Generative Adversarial Network
Generative adversarial networks (GAN) are a class of generative machine learning frameworks. A GAN consists of two competing neural networks, often termed the Discriminator network and the Generator network. GANs have been shown to be powerful generative models and are able to successfully generate new data given a large enough training dataset.
Official Code for DragGAN (SIGGRAPH 2023)
SoftVC VITS Singing Voice Conversion
Image-to-Image Translation in PyTorch
Bringing Old Photo Back to Life (CVPR 2020 oral)
A list of all named GANs!
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Image-to-image translation with conditional adversarial nets
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Build your neural network easy and fast, 莫烦Python中文教学
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
Synthesizing and manipulating 2048x1024 images with conditional GANs
Curated list of awesome GAN applications and demo
Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学
Interactive Image Generation via Generative Adversarial Networks
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Compute FID scores with PyTorch.
[CVPR2020] Adversarial Latent Autoencoders
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.