Tyler Luan

AnimateDiff-I2V. AnimateDiff I2V version.

AI_power. AI toolbox and pretrain models.

huawei_2018_eval. :mag:Evaluate your result. Only support python now.

face_power. Face_lib separate from AI_Power

huawei-code-craft-2018. 华为2018软件精英挑战赛初赛代码，pure python without numpy，实现拉格朗日均值、线性回归、随机森林、指数平滑、模拟退火等算法。

-TopFreeProxies. TopFreeProxies

miaoya_pipeline. 猜测妙鸭实现证件照生成的pipeline

awesome-papers-are-all-you-need. CV-engineering-releated papers and codes.

XSegNet2onnx. convert DeepFaceLab XSegNet's *.npy weights to onnx file

chatGPT_wx_bot. chatGPT weixin bot

cv2box. A gather of tools or funcs frequently using in my work.

MillionHeroes. :video_game:百万英雄/冲顶大会/芝士超人答题助手

SIM7100-Serial-Communication. 3G/4G模块通用的串口通信例程

Init-Gitment. 自动初始化博客中的gitment评论

dd-punch. :alarm_clock:加入虚拟定位，基于触动精灵和天下游的钉钉自动打卡脚本。

SIM7100-dial-script. :phone:dial script of SIM7100 3G/4G模块拨号上网脚本

Waifu-Labs. Unofficial implementation of the Waifu Labs

awesome-audio-driven-digital-human. Focusing on the progress of the audio-driven digital human industry.

langchain-ChatGLM. langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识的 ChatGLM 问答

backtrader_plotting. Plotting addon for backtrader to support Bokeh (and maybe more)

weshop_pipeline. 复现weshop的人台模特换装效果

ykk648.github.io. The repository of my static blog -----

Hyperlpr_for_Windows. 使用PyQt开发的基于Hyperlpr车牌识别的Windows程序。

ReHiFace-S. Real Time High-Fidelity Faceswap

danbooru-utility. Utility for working with danbooru2018 dataset

mmpose. OpenMMLab Pose Estimation Toolbox and Benchmark.

akshare. AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库

bigdetection. BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

multical. Multi-camera calibration using one or more calibration patterns

pose2sim. This Python repository offers a way to perform a markerless kinematic analysis from multiple calibrated views as a unified workflow from an OpenPose input to an OpenSim result.

mmhuman3d. OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

backtrader. Python Backtesting library for trading strategies

ViTPose. PyTorch implementation of ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

ComfyUI-WanVideoWrapper. Python

apstone. Python

stylegan2-ada-pytorch. StyleGAN2-ADA - Official PyTorch implementation

modelscope. ModelScope is committed to empowering a wide-spectrum of developers to leverage AI models from various domains. (致力于通过开放的社区合作，开源AI模型以及相关创新技术，推动基于模型即服务的生态繁荣发展。)

Hand3DResearch. Python

eft. visualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)

mmyolo. OpenMMLab YOLO series toolbox and benchmark

mmdetection. OpenMMLab Detection Toolbox and Benchmark

awesome-talking-head-generation.

Step-Audio. Step-Audio-TTS-3B demo

py39-mathutils. Update mathutils to support python3.9.

cocoapi. Clone of COCO API - Dataset @ http://cocodataset.org/ - with changes to support Windows build and python3

subconverter. backup

extrinsic2pyramid. Visualize Camera's Pose Using Extrinsic Parameter by Plotting Pyramid Model on 3D Space

neural_renderer. A PyTorch port of the Neural 3D Mesh Renderer

VideoChat. 实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

duix.ai. offline 2d digitalhuman demo for edge devices (android/ios/etc.)

argus. 利用github actions跟踪一些仓库的每日更新

reverse-interview-zh. 技术面试最后反问面试官的话

show-me-the-code-python. :sunny:Python版本Show me the code。 Idea来自网络，代码全部重写。

DFDNet. Blind Face Restoration via Deep Multi-scale Component Dictionaries (ECCV 2020)