A games launcher for GOG, Amazon and Epic Games for Linux, Windows and macOS.

A collection of papers on Diffusion for Image-to-Image Translation and Style Transfer

Code for TPAMI "Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Data"

Image-to-Image Translation in PyTorch

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

Nano vLLM

Powerful AI Client

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

PyTorch implementation of DreamerV2 model-based RL algorithm

Mastering Atari with Discrete World Models

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

卡码网-23种设计模式精讲，每种设计模式都配套代码练习题，支持 Java，CPP，Python，Go🔥

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

Overview and tutorial of the LangChain Library

Bazzite makes gaming and everyday use smoother and simpler across desktop PCs, handhelds, tablets, and home theater PCs.

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]

include stereo calibration ,unwrapped phase, matching, 3D reconstruction , point cloud process et al.

Phase map retrieval for fringe projection profilometry and off-axis digital holographic interferometry

【A simple used C++ threadpool】一个简单好用，性能优异的，跨平台的C++线程池。欢迎 star & fork

Refine high-quality datasets and visual AI models

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

based on C++11 , a mini threadpool , accept variable number of parameters 基于C++11的线程池,简洁且可以带任意多的参数

A Detailed Cplusplus Concurrency Tutorial 《C++ 并发编程指南》

Fast and memory-efficient exact attention

Armbian for onecloud. 玩客云用armbian

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers a…

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.