Swap your face in realtime to someone's else.

StyleGAN2 - Official TensorFlow Implementation

Modifications of the official PyTorch implementation of StyleGAN3. Let's easily generate images and videos with StyleGAN2/2-ADA/3!

fast style transfer on your webcam, with pre-trained models at

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

StyleGAN2 - Colab Notebook containing code for training + visualization + projection

Neural Artistic Style in Python

StyleGAN2 - Official TensorFlow Implementation with practical improvements

Code for the paper "Language Models are Unsupervised Multitask Learners"

StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation

Synthesizing and manipulating 2048x1024 images with conditional GANs

Clone a voice in 5 seconds to generate arbitrary speech in real-time

StyleGAN - Official TensorFlow Implementation

Slight modifications to the official StyleGAN2 implementation

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

GuitarML fork for training NeuralPi models

Inkscape GCode Exporter for K40 laser cutters running Marlin

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

StyleGAN2-ADA - Official PyTorch implementation

Pioneer Networks: Progressively Growing Generative Autoencoder

Handwritten Text Generation

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/

Webcam demo for SKTBrain/DiscoGAN

Very Simple and Basic Implementation of Compositional Pattern Producing Network in TensorFlow

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/

Synthesizing and manipulating 2048x1024 images with conditional GANs

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

The Deep Visualizer uses BigGAN (Brock et al., 2018) to visualize music.

Synthesizing and manipulating 2048x1024 images with conditional GANs