All Algorithms implemented in Python

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Let us control diffusion models!

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

StyleGAN - Official TensorFlow Implementation

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Stable Diffusion web UI

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

🔥 2D and 3D Face alignment library build using pytorch

Real-Time High-Resolution Background Matting

StyleGAN2-ADA - Official PyTorch implementation

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

Solving the Traveling Salesman Problem using Self-Organizing Maps

Flickr-Faces-HQ Dataset (FFHQ)

LPIPS metric. pip install lpips

Denoising Diffusion Probabilistic Models

Compute FID scores with PyTorch.

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

Flops counter for convolutional networks in pytorch framework

Summary of related papers on visual attention. Related code will be released based on Jittor gradually.

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

StyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)

Colour Science for Python

VMamba: Visual State Space Models，code is based on mamba

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two