A collection of resources on digital human including clothed people digitalization, virtual try-on, and other related directions.

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

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

A latent text-to-image diffusion model

High-Resolution Image Synthesis with Latent Diffusion Models

Repo for external large-scale work

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

Chinese version of GPT2 training code, using BERT tokenizer.

A multilingual dialog corpus

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

Text-to-video generation.

FewCLUE 小样本学习测评基准，中文版

🌈 NERpy: Implementation of Named Entity Recognition using Python. 命名实体识别工具，支持BertSoftmax、BertCrf、BertSpan等模型，开箱即用。

Artistic Radiance Fields

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

即时通讯IM

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

ZenML 🙏: MLOps framework to create reproducible pipelines.

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.