crywang

DeepFaceLab

DeepFaceLab is the leading software for creating deepfakes.

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

Awesome-Diffusion-Models

A collection of resources and papers on Diffusion Models

undetected-chromedriver

Custom Selenium Chromedriver | Zero-Config | Passes ALL bot mitigation systems (like Distil / Imperva/ Datadadome / CloudFlare IUAM)

puppeteer-extra

💯 Teach puppeteer new tricks through plugins.

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

recognize-anything

Open-source and strong foundation image recognition models.

LyCORIS

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

Awesome-Image-Inpainting

A curated list of image inpainting and video inpainting papers and resources

IQA-PyTorch

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

Awesome-Image-Quality-Assessment

A comprehensive collection of IQA papers

Awesome-Deepfakes-Detection

A list of tools, papers and code related to Deepfake Detection.

linear-attention-transformer

Transformer based on a variant of attention that is linear complexity in respect to sequence length

Ebook-Linear_Programming

ipv6

IPv6 文档

homebrew-cask-drivers

💀 Casks of Drivers (deprecated)

FOXTracker

Facial Head Pose Tracker for Gaming

ArDNSPod

基于DNSPod用户API实现的纯Shell动态域名客户端

AudioDVP

AudioDVP:Photorealistic Audio-driven Video Portraits

EDTER

EDTER: Edge Detection with Transformer, in CVPR 2022

ATVGnet

CVPR 2019

DATID-3D

[CVPR 2023] Official implementation of "DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model"

EveryDream

Advanced fine tuning tools for vision models

watermark-tracer

一个基于可视水印检测识别的数字媒体溯源应用系统，是我的大作业项目，包含这个系统以及一个开源的大规模常见水印图像数据集（Large-scale Common Watermark Dataset, LCWD）。 输入一个带有可视水印的图片或视频，系统会检测定位到水印所在的区域，然后将其提取出来，然后借助百度AI开放平台的OCR和logo识别以及Bing搜索引擎，溯源到这个图片或视频的源头。

home_for_adser

some useful papers and blogs for people who are interested in online advertising

Adobe-GenP

A universal activator for Adobe CC 2019 and later products on Windows

UAED

bupTemplate

Latex template rescuing PhDs in BUPT from dissertations typesetting.

mesh-to-depth

Depth map generator for Python written in C++