#
Starred repositories
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
[AAAI2024] FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning
Keyphrase or Keyword Extraction 基于预训练模型的中文关键词抽取方法（论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model 的中文版代码）
zi2zi implement with pytorch
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
JavaScript package for predictive data analysis and machine learning
Fast, Flexible and Portable Structured Generation
PyTorch-based differentiable material graph library for procedural material capture
Single-Image SVBRDF Capture with a Rendering-Aware Deep Network
Get your documents ready for gen AI
A self-organizing file system with llama 3
⚡️基于物理的渲染（PBR）白皮书 | White Paper of Physically Based Rendering(PBR)
经典编程书籍大全，涵盖：计算机系统与网络、系统架构、算法与数据结构、前端开发、后端开发、移动开发、数据库、测试、项目与团队、程序员职业修炼、求职面试等
Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA
soswow / fit-curve
Forked from volkerp/fitCurvesJavaScript implementation of Philip J. Schneider's "Algorithm for Automatically Fitting Digitized Curves" from the book "Graphics Gems". Converted from Python implementation.
Official inference repo for FLUX.1 models
Online Handwritten Text Recognition (HTR) system implemented with PyTorch. Based on https://doi.org/10.1007/s10032-020-00350-4.
SRD: A Tree Structure Based Decoder for Online Handwritten Mathematical Expression Recognition
Evaluation of different machine learning models on the task of online handwritten character recognition
Track, Attend and Parse for Online Handwritten Mathematical Expression Recognition
Python library and tools for online handwritten Chinese character recognition
[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.