🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Related papers for reinforcement learning, including classic papers and latest papers in top conferences

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

中文 LLaMA-2 & Alpaca-2 大模型二期项目 + 本地CPU/GPU训练部署 (Chinese LLaMA-2 & Alpaca-2 LLMs)

Port of Facebook's LLaMA model in C/C++

Release for Improved Denoising Diffusion Probabilistic Models

Exploiting Diffusion Prior for Real-World Image Super-Resolution

Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"

High-Resolution Image Synthesis with Latent Diffusion Models

Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"

The Go-To Choice for CV Data Visualization, Annotation, and Model Analysis.

papers about Face Reenactment/Talking Face Generation

Interactive semi-automatic image segmentation annotation tool.（交互式半自动图像分割标注工具）

High-Resolution Image Synthesis with Latent Diffusion Models

A Toolkit for Text-to-Video Generation and Editing

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Noise supression using deep filtering

Dataset and Code for MIPI2022 Challenge

Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

Dense matching library based on PyTorch

Code for the paper Learned Vertex Descent: A New Direction for 3D Human Model Fitting (ECCV 2022)

Official PyTorch implementation for the paper High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions.