Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

This project aim to reproduce Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.

Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

A curated list of face restoration & enhancement papers and resources

Repository for "HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling". [CVPR2023 Highlight]

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

Text-to-face implementation using AttnGan architecture.

Pytorch implementation of human body SMPL model, support GPU training, batch processing and joint regression.

Faceunity 面部跟踪和虚拟道具 SDK 在 PC 平台中的集成 Demo

an android alternative implementation for unreal face live link

【AAAI 2021】MVFNet: Multi-View Fusion Network for Efficient Video Recognition

StyleGAN Encoder - converts real images to latent space

Caffe: a fast open framework for deep learning.

Retinaface pytorch face-pose-detect face-key-point-detect

This branch is developed for deep face recognition

Convert MXNet model to Caffe model

A Python Perceptual Image Hashing Module