StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

Official PyTorch implementation of StyleGAN3

PyTorch package for the discrete VAE used for DALL·E.

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 ext…

Official code for paper "Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors"

A Framework for Encrypted Machine Learning in TensorFlow

Code and models for evaluating a state-of-the-art lip reading network

Tensorflow implementation of Generative Latent Optimization (GLO) proposed by Facebook AI Research

Spatial Audio Generation

A Keras CTC implementation of Baidu's DeepSpeech for model experimentation

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Out of time: automated lip sync in the wild

A method to generate speech across multiple speakers