Document to Markdown OCR library with Llama 3.2 vision

Zotero chat PDF with AI, DeepSeek, GPT 4.1, ChatGPT, Claude, Gemini, Qwen3

Interface for OuteTTS models.

[CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

[768 Resolution] [Any "SDXL" Model] [Various Conditions] [Texture Synthesis] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

Initialize popular chatbots and apply responses with a single click.

Unifying 3D Mesh Generation with Language Models

一个轻量级、支持全链路且易于二次开发的大模型应用项目(Large Model Data Assistant) 支持DeepSeek/Qwen2.5等大模型 基于 Dify 、Ollama&Vllm、Sanic 和 Text2SQL 📊 等技术构建的一站式大模型应用开发项目，采用 Vue3、TypeScript 和 Vite 5 打造现代UI。它支持通过 ECharts 📈 实现基于大模型的数据图形化问答，具备处理 CSV 文件 📂 表格问答的能力。同时，能方便对接第三方开源 RAG 系统 检索系统 🌐等，以支持广泛的通用知识问答。

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

A hub for various industry-specific schemas to be used with VLMs.

A lightning-fast, cross-platform AI chat application built with React Native.

GPT-4o and Claude-3.7-Sonnet APIs for coding.

User-friendly Enterprise Ready AI Interface (Supports Ollama, OpenAI API, DeepSeek...)

CodeGate: CodeGen Privacy and Security

A Survey of Spoken Dialogue Models (60 pages)

Generate Diffuse Textures on Meshes directly in Blender 3D with Stable Diffusion.

📚FFPA(Split-D): Yet another Faster Flash Attention with O(1) GPU SRAM complexity large headdim, 1.8x~3x↑🎉 faster than SDPA EA.

Code for ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

UnrealMCP is here!! Automatic blueprint and scene generation from AI!! An Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. Supports Claude Desktop App, Windsurf & Cursor, also includes OpenAI's GPT4o, DeepseekR1, Claude Sonnet 3.7 APIs and Grok 3, with plans to add Gemini, audio & realtime APIs soon.

GLM Series Edge Models

LLM4AD: A Platform for Algorithm Design with Large Language Model

Benchmarking Agentic LLM and VLM Reasoning On Games

Run Local and API LLMs, Features Gemini2 image generation, DEEPSEEK R1, QwenVL2.5, QWQ32B, Ollama, LlamaCPP LMstudio, Koboldcpp, TextGen, Transformers or via APIs Anthropic, Groq, OpenAI, Google Gemini, Mistral, xAI and create your own charcters assistants (SystemPrompts) with custom presets

Implementation of the board game Codenames, re-imagined as a collaborative game between LLM agents

The PyVisionAI Official Repo

Official code for "LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models" (CVPR 2025)

📁 This repository contains end-to-end AI blueprint projects designed to run effortlessly across a wide range of use cases; including data science, machine learning, deep learning, and generative AI. 🛠️ All projects are built using HP AI Studio with ❤️ If you find this useful, please don’t forget to star the repository ⭐ and support our work 🚀

Build AI powered websites with Astro, Shadcn and Vercel AI SDK

A most Frontend Collection and survey of vision-language model papers, and models GitHub repository

Enhance and modify high-quality compositions using real-time rendering and generative AI output without affecting a hero product asset.

SDXL Training Improvements

OLA-VLM: Elevating Visual Perception in Multimodal LLMs with Auxiliary Embedding Distillation, arXiv 2024

GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks

End-to-End Navigation with VLMs

Collection of PDF parsing libraries like AI based docling, claude, openai, llama-vision, unstructured-io, and pdfminer, pymupdf, pdfplumber etc for efficient snapshot, text, table, and metadata extraction.

A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository aggregates surveys, blog posts, and research papers that explore how LMMs represent, transform, and align multimodal information internally.

Automation framework in TypeScript and Playwright

Concatenated documentation for use with LLMs

Build-An-LLM-RAG-Chatbot-With-LangChain-Python

The prompts which could enable GPT-4o to think and act like GPT-o1-mini

🤖 AI-powered food analysis tool that instantly calculates calories and nutrients from images. Built with Next.js 15, Vercel AI SDK, and GPT-4o.

Web UI for gptme, built with lovable.dev

最新Poe订阅教程：国内如何充值购买Poe会员账号？可无限制使用GPT-4o生图功能、GPT-4.1系列模型、Claude-Sonnet/Opus-4、满血版DeepSeek-R1、马斯克Grok-3、谷歌Gemini-2.5 Pro等！本文将手把手地教大家如何快速申请一张“WildCard野卡信用卡”，并使用该卡为Poe充值。而且，本Poe订阅教程经过亲测，真实有效且安全可靠，整个Poe购买流程最快仅需十五分钟即可完成。

[NeurIPS 2024] official code release for our paper "Revisiting the Integration of Convolution and Attention for Vision Backbone".

Ask Me Anything for any website, powered by Firecrawl and OpenAI GPT-4o-mini

AI Frontiers Digest leverages LLMs to intelligently curate and summarize the latest developments in AI, while also generating engaging Podcasts.

Real-time GPT-4o video/photo/voice chat

ChatGPT中文版：国内访问指南（支持 GPT-4、GPT-4o、GPT-o1，无需翻墙）【5月持续更新】ChatGPT中文版、ChatGPT官网、ChatGPT网页版，本文提供完整的 ChatGPT 中文版使用指南，推荐国内可用的 ChatGPT 镜像网站，支持 GPT-4、GPT-4o，永久免费，无需翻墙，适合中文用户。 本项目旨在为用户提供一站式的 ChatGPT 中文版使用指南，同时整理了国内可用的 ChatGPT镜像网站 和 官网使用教程，帮助您快速上手 ChatGPT，无论是个人使用还是专业需求。

一个基于 AI 的面试模拟系统，支持实时语音对话和多种面试场景。通过结合 OpenAI 的 GPT、Whisper 和 TTS 技术，为用户提供沉浸式的面试体验。

My LLM Templates (Ollama Modelfiles & Tabby Templates + Presets)

Run SD1.x/2.x/3.x, SDXL, and FLUX.1 on your phone device

A powerful, unofficial OpenAI-compatible API service offering free access to GPT-4o, GPT-4-turbo, and audio preview models like gpt-4o-audio-preview & Realtime Models like gpt-4o-realtime. Features streaming responses, voice synthesis, TTS with no authentication requirements. Hosted on Hugging Face & Railway (Free tier)

This repository contains a series of samples on how to analyse a video using multimodal Large Language Models, like GPT-4o or GPT-4o-mini.

Repository for the paper: Teaching VLMs to Localize Specific Objects from In-context Examples

Can GPT solve Brazilian university entrance exams?

The code for "VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation" [CVPR2025]

Easy MCP (Model Context Protocol) servers and AI agents, defined as YAML.

从零开始基于 LangGraph 和 Streamlit 实现基于本地模型的 RAG、Agent 应用

A unified interface for various AI model providers

A behavioral testing library for LLM applications that allows developers to write natural language specifications for unit and integration tests. Validate LLM application behavior using plain English assertions in a simple assert(str, str) form factor.

PyCon mini 東海 2024 のトーク「Google Colaboratoryで試すVLM」で紹介したサンプル集

[CVPR 2025] Official repository of SoRA: Singular Value Decomposed Low-Rank Adaptation for Domain Generalizable Representation Learning

Computer Agent Arena Hub: Compare & Test AI Agents on Crowdsourced Real-World Computer Use Tasks

Automatically remove watermarks from illustrations using AI (Stable Diffusion).

Lecca.io | AI Agents & Automations

This project leverages Large Language Models (LLMs) and a multi-agent framework to analyze stock prices, gather relevant news, and generate comprehensive financial investment reports for companies.

INFRA-COMPASS is a tool that leverages Large Language Models (LLMs) to create and maintain an inventory of state and local codes and ordinances applicable to energy infrastructure.

An AI chatbot plugin for Obsidian using the Gemini API for note summarization, content generation, and more. Enhance your workflow with AI assistance like the Notion AI bot.

🤖 AI-Powered VSCode extension for generating standardized Git/SVN commit messages. ✨ Supports multiple AI services: OpenAI, ChatGPT, Ollama, Zhipu, DashScope, Doubao, Gemini and VS Code built-in AI. 🌍 Multi-language support (EN/CN/JP/KR/Other). 📊 Auto-generate weekly reports.

Korean SAT leader board

AI Gemini

A NFT Marketplace powered by Generative AI for creating NFT assets using Stable Diffusion, DALL-E and Midjourney.

(WIP) 🦀 An Insanely Fast 🚀 Full Stack Content Generation SaaS Platform Powered by Dioxus, Dioxus Server Functions, Axum, Unsplash, Gemini AI & MongoDB.

ChatGPT中文版：国内访问指南（支持GPT-4，无需魔法，无限使用GPT-4o和o1）

呼叫中心，智能外呼，大模型呼入机器人，大模型呼出机器人，客服系统，工单系统，开源呼叫中心系统，话务系统，智能外呼系统，智能电话外呼，呼叫中心系统，大模型客服，电话外呼，客服中心，在线客服，大模型呼叫中心，呼入机器人，大模型机器人，智能电话外呼，开源呼叫中心系统，电话外呼，在线客服，大模型callcenter,contactcenter,Call，IPCC，Customer Service，Voice，AI，Call Center, Contact Center,LLM,TTS,ASR,NLP,Chabot,FreeSWITCH,OpenSips,Kamailio,Asterisk,WebRTC,Robot,Outbound,LangChain,RAG！

Dump your codebase into single file, so you can use it as an input to LLMs, like ChatGPT, Google Gemini (directly or through or Google AI Studio), Claude and others. This project is the lightweight version of Codebase Digest - check it for example LLM prompts.

A low latency, fault tolerant API for accessing LLM's written in C++ using llama.cpp.

REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model

Run llama.cpp server with Vulkan

<综合> Funasr语音识别，调用Qwen大模型回答，通过GPTSovits输出语音的ai程序，其中调用模型还是在线，后续将添加离线大模型

Construct a Tri-Training framework using VLMs as base estimators, and evaluate its accuracy on multiple semi-supervised learning benchmarks.

Customized Cover Letter PDF Generator using OpenAI's GPT-4o model

This project provides tools to load and prune large language models using a structured pruning method.

A browser extension that helps you summarize web content and YouTube videos using your existing AI accounts (ChatGPT, Claude, or Gemini). Hence it's free!

[ICCV 25] Official repository of "Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues"

Pretrained Keras 3 vision models with custom layers, including object detection, segmentation, and vision-language models (VLMs), with backbone support.

A python sdk for LLM finetuning and inference on runpod infrastructure

[ICCV 2025] Geminio is a VLM-powered gradient inversion attack in federated learning (FL). It allows the adversary (the FL server) to describe the data of value and reconstruct the victim client's private data matching the description.

Data Reduction Pipeline for the Magellan LLAMAS Integral Field Spectrograph

Revolutionizing learning through AI-powered flashcards and adaptive study methods.

🐱🐾基于大模型的 ACM-ICPC 算法题目自动出题系统，可以自动生成算法题目、测试用例和题解代码。系统可以作为一个单独的服务运行，也可以作为一个模块集成到 OJ 系统中。