A lightweight, powerful framework for multi-agent workflows

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

🇨🇳 Chinese sticker pack,More joy / 表情包的博物馆, Github最有毒的仓库, 中国表情包大集合, 聚欢乐~

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Generate a transcript for your favourite Manga: Detect manga characters, text blocks and panels. Order panels. Cluster characters. Match texts to their speakers. Perform OCR.

GRUtopia: Dream General Robots in a City at Scale

Enjoy the magic of Diffusion models!

A simple open-sourced SigLIP model finetuned on Genshin Impact's image-text pairs.

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

Implementation of AAAI2021 paper "Writing Polishment with Simile: Task, Dataset and A Neural Approach"

Parsing Hoyoverse game text corpus from public wikipedia

A project that extracts Honkai: Star Rail text corpus

[ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

A high-throughput and memory-efficient inference and serving engine for LLMs

✨✨Latest Advances on Multimodal Large Language Models

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

Bubble Blaster removes text from speech bubbles in mangas/manhwas, made for Scanlations groups.

Characterize Anything: A Wondrous Chemical Reaction between vision models and AI Characters

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

OSLO: Open Source framework for Large-scale model Optimization

Extracting character conversations in Genshin Project

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

Deezer source separation library including pretrained models.

Pytorch implementation for few-shot photorealistic video-to-video translation.

Non-Monotonic Sequential Text Generation (ICML 2019)

Must-read Papers on pre-trained language models.

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型