MEIZU16

ragflow

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

agentscope

Start building LLM-empowered multi-agent applications in an easier way.

colibri

:bird: Modify your Ajax requests to test

EasySpider

A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。

SillyTavern-Docker

weekly

科技爱好者周刊，每周五发布

anti-AD

致力于成为中文区命中率最高的广告过滤列表，实现精确的广告屏蔽和隐私保护。anti-AD现已支持AdGuardHome，dnsmasq， Surge，Pi-Hole，smartdns等网络组件。完全兼容常见的广告过滤工具所支持的各种广告过滤列表格式

rembg

Rembg is a tool to remove images background

Umi-OCR

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

better-genshin-impact

📦BetterGI · 更好的原神 - 自动拾取 | 自动剧情 | 全自动钓鱼(AI) | 全自动七圣召唤 | 自动伐木 | 自动刷本 | 自动采集 - UI Automation Testing Tools For Genshin Impact

GeneFace

GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code

IT-Company-Website

The project “IT Company Website” is a responsive website made using HTML, CSS, Bootstrap and JavaScript.

koodo-reader

A modern ebook manager and reader with sync and backup capacities for Windows, macOS, Linux and Web

FreeU

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

VQ-Font

[AAAI2024] Official PyTorch implementation of VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization.

DanDanPlayForAndroid

弹弹play 概念版，弹弹play系列应用安卓平台上的实现，是一个提供了视频播放（本地+局域网）和弹幕加载（在线+本地）功能的本地播放器

ICCV2023-Papers-with-Code

ICCV 2023 论文和开源项目合集

OnmyojiAutoScript

Onmyoji Auto Script | 阴阳师脚本

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

CnSTD

CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包

sam-pt

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

poe-api

[UNMAINTAINED] A reverse engineered Python API wrapper for Quora's Poe, which provides free access to ChatGPT, GPT-4, and Claude.

RelateAnything

Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.

NAFNet

The state-of-the-art image restoration model without nonlinear activation functions.

TextLogoLayout

[CVPR 2022] Aesthetic Text Logo Synthesis via Content-aware Layout Inferring

seq2seq-layout-analysis

end2end layout analysis based seq2seq

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

GPT-4-LLM

Instruction Tuning with GPT-4

DoctorGLM

基于ChatGLM-6B的中文问诊模型

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。