Models and examples built with TensorFlow

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

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

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

StyleGAN2 - Official TensorFlow Implementation

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

High-Resolution 3D Human Digitization from A Single Image.

Hydra is a framework for elegantly configuring complex applications

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Official PyTorch implementation of StyleGAN3

Model parallel transformers in JAX and Haiku

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

StyleGAN2-ADA - Official PyTorch implementation

Denoising Diffusion Probabilistic Models

NVIDIA's Deep Imagination Team's PyTorch Library

Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts

CUDA Python: Performance meets Productivity

[NeurIPS'21] Projected GANs Converge Faster

Official implementation of the paper "Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis" in ICLR 2021

Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)

Tensorflow implementation of Learning-based Video Motion Magnification

Video and Image Analytics for Multiple Environments

Implementation of Stochastic Image-to-Video Synthesis using cINNs.

[ECCV 2022] Official Pytorch implementation of "Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis"

Marine debris detection with commercial satellite imagery and deep learning.

Flickr Diverse Faces (FDF) is a dataset with 1.5M faces "in the wild".