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

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)

CLI LLM tool

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.

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

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.

<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

Can GPT solve Brazilian university entrance exams?

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)

its 1.0 version ( development at its initial stage)

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

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.

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.

Langevin Monte Carlo

Local Chatbot with Llama 3.2 Model and Ollama

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.

MycodeGpt

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.

Korean SAT leader board

Developing a LLM based on LLaMA 3.1 for tasks related to korean - english educational contents using LLaMA factory

gpt_wn

We will

Automates filling cashback category information from banks using a Telegram Bot integrated with Vision Language Models (VLM) for image processing and the Notion API for organized data storage

Evaluating Vision-Language Models for Detecting and De-identifying Protected Health Information Burn-in on Medical Images

A Python package to extract text from images and PDFs using Vision Language Models (VLM).

🎥 Create parody videos from uploaded files. Created in preparation for Sora.

Config files for my GitHub profile.

Sora JS SDK を使った zztkm の個人的サンプル集

Config files for my GitHub profile.

Docker setup to run Stable diffusion on 3070

Personalized Stable Diffusion featuring text-guided horizontal and vertical partition controllers to apply distinct prompts across specific image regions

StableDiffusion3.5の最低限UI

Swagify is a 3D T-shirt customization app built with React, Three.js, and Tailwind CSS. Users can personalize T-shirts with colors, logos, and AI-generated textures via Stable Diffusion API integrated with FastAPI in Python. This app merges real-time 3D design with AI for a unique styling experience.

Images and Prompts Generation Using Stable Diffusion and GPT2

Uses stable diffusion to generate images

This repository provides a comprehensive setup and execution guide for fine-tuning Stable Diffusion XL using LoRA (Low-Rank Adaptation) with Hugging Face's Diffusers library.

Built a comprehensive pipeline that generates images from text descriptions using Stable Diffusion, analyzes them using CLIP, and performs instance segmentation using Meta’s Segment Anything Model 2 (SAM2). T

Face Extractions for training Stable Diffusion LoRA networks

In-depth implementation of Stable Diffusion

task for superteams.ai

SDXL

Powered by OpenAI using gpt-4o, I created an AI Assistant named 'Kiwi'. Kiwi the QE is an intelligent assistant designed to streamline the software testing process by automating the creation of test cases and providing expert feedback on existing ones. This tool ensures that your test cases are thorough, accurate, and aligned with best practices.

A work in progress application that will utilize gpt-4o to generate questions based on content using assistants.

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

A GPT-4O clone using text to speech, function calling with news and web search APIs for realtime data retrieval

Nova AI - An AI-powered chat application built with Flutter, integrating Gemini AI for real-time, interactive conversations. Features include persistent chat history, smart suggestions, and a modern, user-friendly interface.