Boycetoon

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

WeChatMsg

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

milvus

A cloud-native vector database, storage for next generation AI applications

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

LLaVA

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

marker

Convert PDF to markdown quickly with high accuracy

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

llm-cookbook

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

hallo

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

LangGPT

LangGPT: Empowering everyone to become a prompt expert!🚀 Structured Prompt，Language of GPT, 结构化提示词，结构化Prompt

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course

WeChatFerry

微信机器人底层框架，可接入Gemini、ChatGPT、ChatGLM、讯飞星火、Tigerbot等大模型。WeChat Robot Hook.

towhee

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

obsidian-copilot

A ChatGPT Copilot in Obsidian

EVA

EVA Series: Visual Representation Fantasies from BAAI

social-auto-upload

自动化上传视频到社交媒体：抖音、小红书、视频号、tiktok、youtube、bilibili

onediff

OneDiff: An out-of-the-box acceleration library for diffusion models.

ComfyUI_InstantID

ComfyUI_TensorRT

ComfyUI_VLM_nodes

Custom ComfyUI nodes for Vision Language Models, Large Language Models, Image to Music, Text to Music, Consistent and Random Creative Prompt Generation

ComfyUI-Anyline

Anyline: A Fast, Accurate, and Detailed Line Detection Preprocessor

style_aligned_comfy

B-LoRA

Implicit Style-Content Separation using B-LoRA

learn-python-the-smart-way-v2

聪明办法学Python，简明且系统的 Python 入门教程第二版。

hugging-sd

Hugging StableDiffusion, Hugging Future.

ComfyUI-Tara-LLM-Integration