tyxsspa

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

Bagel. Open-source unified multimodal model

AnyStory. AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation

FramePack. Lets make video diffusion practical!

AnyText2. Official implementation code of the paper <AnyText2: Visual Text Generation and Editing With Customizable Attributes>

OminiControl. [ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

ELLA. ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Glyph-ByT5. [ECCV2024] This is an official inference code of the paper "Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering" and "Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering""

HunyuanDiT. Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

AnyText. Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

StableCascade. Official Code for Stable Cascade

ReplaceAnything.

AnyText-colab. Jupyter Notebook

dreamoving-project. Official implementation of DreaMoving

paddle2torch_PPOCRv3. Python

pytorch-fid. Compute FID scores with PyTorch.

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

lora-scripts. SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

clip-interrogator. Image to prompt with BLIP and CLIP

ml-visuals. 🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

xtreme1. Xtreme1 is an all-in-one data labeling and annotation platform for multimodal data training and supports 3D LiDAR point cloud, image, and LLM.

Awesome-3D-Object-Detection. Papers, code and datasets about deep learning for 3D Object Detection.

BBox-Keypoint-Label-Tool. 一个对应目标边界框标注关键点的标注工具，GUI基于tkinter编写。

Generative-Art. A hub for all of my generative art projects

tesseract. Tesseract Open Source OCR Engine (main repository)

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

PytorchOCR. 基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

lightweight-neural-architecture-search. This is a collection of our zero-cost NAS and efficient vision applications.

mmcv. OpenMMLab Computer Vision Foundation

mmdetection. OpenMMLab Detection Toolbox and Benchmark

InsightFace-REST. InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.

tensorrt_inference. C++

TFace. A trusty face analysis research platform developed by Tencent Youtu Lab

yolov5. Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

arxiv-sanity-preserver. Web interface for browsing, search and filtering recent arxiv submissions

FaceImageQuality. Code and information for face image quality assessment with SER-FIQ

Modified-CBAMnet.mxnet. A MXNet implementation of Modified CBAMnet.mxnet

CBAM.PyTorch. Non-official implement of Paper：CBAM: Convolutional Block Attention Module

pycls. Codebase for Image Classification Research, written in PyTorch.

VarGFaceNet. Python

documentation. Issue tracker for Plotly's open-source documentation.

AdaptiveFace.

Matrix_Derivatives. This is a note on matrix derivatives and described my own experience in detail. Hope you'll like it.

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

PlotNeuralNet. Latex code for making neural networks diagrams

labelme. Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

TP-GAN. Official TP-GAN Tensorflow implementation for paper "Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis"

deep_learning_object_detection. A paper list of object detection using deep learning.

cdp. Code for our ECCV 2018 work.

GAN_gluon_tutorials. This tutorial of GAN is Chinese translation of its English version which is created by MXNet group.

ganhacks. starter from "How to Train a GAN?" at NIPS2016

daily-paper-computer-vision. 记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文

Modified-CRUNet-and-Residual-Attention-Network.mxnet. :fire::fire:A MXNet implementation of Modified CRUNet & Residual Attention Network:fire::fire:

crnn.mxnet. crnn in mxnet.can train with chinese characters

deep-learning-papers-translation. 深度学习论文翻译，包括分类论文，检测论文等

labelImg. LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data.

Face-Liveness-Detection. Face Liveness Detection in C++ and MATLAB.

gluon-cv. Gluon CV Toolkit

mxnet-im2rec_tutorial. this simple tutorial will introduce how to use im2rec for mx.image.ImageIter , ImageDetIter and how to use im2rec for COCO DataSet

FaceKit. [CVPR 2018] Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

TextBoxes_plusplus. TextBoxes++: A Single-Shot Oriented Scene Text Detector

HyperLandmark. Deep Learning Based Free Mobile Real-Time Face Landmark Detector. Contact:jack-yu-business@foxmail.com

SSR-Net. [IJCAI18] SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation

TextBoxes. TextBoxes: A Fast Text Detector with a Single Deep Neural Network

ImageCaptioning.pytorch. I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

rude-carnie. Age detection in Tensorflow

age-gender-estimation. Keras implementation of a CNN network for age and gender estimation

Fast-MTCNN. a casual work about retraining to optimize mtcnn Pnet and ONet. it can achieve 100+fps on CPU with minSize 60 (1920x1080) on intel i7 6700k

d2l-zh. 《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

mxnet_mtcnn_face_detection. MTCNN face detection

caffe_ocr_for_linux. C++

mxnet. Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

openface. Face recognition with deep neural networks.

OpenFaceIOS. OpenFace is get from https://github.com/TadasBaltrusaitis/OpenFace, a state-of-the art open source tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation. And I create an ios project. Delete Dlib,TBB,Boost. Only use OpenCV .

fast-face-android. 👦 Fast-Face : Android App for Real-time Face Landmark Detection. You can check your landmarks in 60ms

OpenFace. OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

insightface. State-of-the-art 2D and 3D Face Analysis Project

Zeusee-Face-Anti-spoofing. 开源配合型人脸活体检测 Open Source Face Anti-spoofing