Github Projects

A revolutionary approach to image editing that perfectly preserves the background during modifications. Edit specific areas precisely while maintaining perfect visual consistency

Quickly create images of a character in different positions while maintaining consistency

Improve the quality and resolution of your images with an open-source tool. Models currently in use: RealCUGAN, RealESRGAN, Waifu2x and SRMD

An open source image enlarger on MAC using AI and available for free on GitHub

An AI under GPT-4 that can accurately describe an image, create a website, generate a story, etc.

A non-generative LLM model that learns by watching videos. It produces excellent recognition and detection results

An open source language model optimized for advanced reasoning, understanding of long contexts (256K tokens) and efficiency on limited resources. Ideal for search, agentic and multilingual processing

Discuss your documents securely via an all-in-one interface compatible with many open-source LLM templates. Powered by Apple MLX framework

Discover the inner workings of GPT in an interactive spreadsheet. See the architecture, matrix calculations and data flow. Fun and instructive

A lightweight multimodal AI model, capable of processing text, image, audio and video on all your devices, even mobile ones. Fast execution, efficient resource management and support for over 140…

A high-performance LLM model that rivals the best open-source models currently available

A code- and text-driven model (LLM) that includes over 80 programming languages and uses text from GitHub and notebooks