Unifying 3D Mesh Generation with Language Models

A Survey of Spoken Dialogue Models (60 pages)

SDXL Training Improvements

End-to-End Navigation with VLMs

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

Youtube:

Can GPT solve Brazilian university entrance exams?

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

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)

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

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.

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

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.

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

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

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

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

Korean SAT leader board

Telegram bot for fast and efficient creation of D&D character

"GovEase" is a simple platform that connects citizens with essential government information and services.

Chat GPT with real time internet search capabilities. Built using Python, LangChain, Streamlit, Open AI, and Google Search Results.

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

CLI LLM tool

Name your screenshots using VLMs

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

Focus on the generation of demonstration animations for mathematics, statistics, etc., based on the Llama large model.

<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

MycodeGpt

A feedback app for mipyme bits in peru using gemini, open ai and a lot diferent and useful integrations(AYNI HACKATON REGIONAL WINNER PROJECT)

LLM-based ESG-Focused Portfolio Optimization Support service (LEPOS) - KWU Industry-Academic Cooperation SW Project 2024 by KWargs

PoseMorphAI is a comprehensive pipeline built using ComfyUI and Stable Diffusion, designed to reposition people in images, modify their facial features, and change their clothes seamlessly. This solution leverages advanced pose estimation, facial conditioning, image generation, and detail refinement modules for high-quality output.

A finance saas integrated with gpt chat

Moondream Web Interface: A modern web interface for the Moondream vision language model, built with Next.js and FastAPI. This project provides a user-friendly way to interact with images using Moondream's vision-language capabilities.

Stable Diffusion + ImageBind = ImageCraft (nothing to do with Minecraft unfortunately)

Analyze pdf documents using Azure OpenAI GPT-4o vision capabilities.

its 1.0 version ( development at its initial stage)

An easy-to-use, fast, and easily integrable tool for evaluating audio LLM

A real-time graphics engine build with OpenGL, GLFW, and GLM.

Automatic collection of free instances of AI text models (ChatGPT, Claude, llama and others)

The Clean-UI project offers an intuitive interface for interacting with Llama-3.2 models, enabling users to generate detailed image descriptions and engage in AI-driven conversations. It includes easy setup instructions and a logging system for tracking interactions, making it ideal for developers and researchers.

A custom extension for ComfyUI that optimizes and deploys Stable Diffusion workflows on Qualcomm Cloud AI 100 accelerators.

An AI Tutor that tailors lessons based on the user's learning style and progress

Llama3 Finetuning for SQL Code Generation

An AI Chatbox developed using the Gemini API, offering interactive, real-time responses for an engaging conversational experience. Built with HTML, CSS, and JavaScript, it features a responsive design, intuitive interface, and smooth animations, showcasing advanced API integration and a user-focused chat experience.

Minimal repository template for project using xmake and opengl

Playable plane render with OpenGL, using glfw, glew, glm.

Haiku Generation and Visualization Dashboard RNN LM NLP Final Project - Spring 2023

Langevin Monte Carlo

Local Chatbot with Llama 3.2 Model and Ollama

SUPIR upscaling wrapper for Forge Webui

Open-Research.ai is an AI-driven search engine that leverages OpenAI and Serper.dev to deliver a powerful search experience. 1-Click deploy to Vercel.

A Git commit message generator powered by OpenAI GPT-4o and Anthropic Claude 3.5

SumTube é uma ferramenta que extrai legendas de vídeos do YouTube e cria resumos concisos com o Google Gemini. A ferramenta permite exibir o conteúdo transcrito e exportar o resumo em PDF, oferecendo uma solução prática e eficiente para obter uma visão geral rápida de vídeos longos.

Sketch&Solve is an iOS18 Math notes inspired app, allowing users to draw, write, and calculate math expressions using the GEMINI API. Built with React, it uses a canvas component where drawings are sent to the API as images for analysis. The API returns results in expression form, which the app renders on the frontend using LaTeX.

ShellGPT is an AI powered command-line tool that suggests and explains shell commands based on natural language queries. Perfect for those cases where you forget how to exit vim!

This is pineapple app to call Chat GPT endpoint. Backend api is fastapi

This is end to end LLM and gen ai project that will use Llama3.1 open source LLM, chromadb (vector store), Langchain and streamlit to build a tool called cold email generator.

Lawyer Llama is an intelligent legal assistant powered by LLaMA specifically designed to provide expert guidance on the Indian Constitution as of 2023. This application provides precise, context-aware legal information by leveraging advanced language models and vector search technology.

SoraDBlite is a Python class designed to simplify interactions with MongoDB databases. And the operation are similar to the mongodb, and it is easy to understand. It is the lite version of pymongo.

Dataset: https://www.kaggle.com/datasets/juliancamilovelandia/logos-with-white-background?select=dataset_annotations_descriptions.json

Colorisation of Manga Image using Stable Diffusion

Discord Bot + Replicate + Stable Diffusion

An AI Artist application utilizing LLM and Stable Diffusion.

Stable diffusion from scratch in PyTorch with full training script and web ui for inference.

Layout for Seamless Image Assembly

RPI + Dual Camera + ChatGPT + Claude + Gemini + Grok + Perplexity + 5" Screen + Speaker&Mic

Full Stack AI Course Generator App With NextJs, React, TailwindCss, Gemini Api, Drizzle

building a financial tracker using LLM

ChatGLM私有化部署聊天机器人

Collection of genomic Language Models

areaone lms is a system where its ctudents can access course materials available in the system.

A novel Fuzzer utilizing Large Language Model for Ethereum Smart Contract Vulnerability Detection.