Trending Projects

A deep learning-based framework for Structure from Motion (SfM) from visual geometry.

LLM-powered fuzzing tool that integrates with the OSS-Fuzz security platform to find bugs in open-source projects.

A Python library that turns any face into a video game character, pixel art, claymation, 3D, or toy using generative AI models.

An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources for mobile and edge AI.

An open-source library for learning continuous image representation using local implicit image function.

A community-driven Python bot that aims to be simple to serve humans with everyday tasks

Samples and examples for the Agent2Agent (A2A) Protocol, a framework for building AI-powered applications.

AttnGAN is a Python library for generating high-quality images from text descriptions using attention-based generative adversarial networks.

A realistic web environment for building autonomous agents and AI-driven applications.

Next-gen AI+IoT framework for fast IoT and AI agent hardware integration

This repository provides valuable resources for researchers working on RL-based Reasoning MLLMs.

3D Procedural Game Engine Using OpenGL for building procedural environments, terrains, and games.

A repository of custom instructions for using the ChatGPT language model effectively.

Supporting code for a short YouTube series on demystifying neural networks.

A library that helps developers train BERT-type language models with limited compute resources.

A robust multi-pedestrian tracking library built with PyTorch, YOLO, and other computer vision techniques.

A powerful conversational AI JavaScript library that supports various LLM providers and integrates with UI frameworks.

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion for AI art and prompt engineering.

A collection of pre-trained computer vision models for developers building AI-powered applications.

A deep learning NLP pipeline implemented on TensorFlow for natural language processing tasks.

This is a library that explores using Fourier features to help neural networks learn high-frequency functions.

A .NET/C# binding for Baidu's Paddle Inference library and PaddleOCR, enabling AI/ML integrations.

A gym for reinforcement learning with verifiable rewards, focusing on reasoning and language models.

A Python tool that generates videos for a YouTube learning channel focused on AI coding tools and workflows.

A Python-based benchmarking framework for evaluating large-scale machine learning models and datasets.

A C++ library for facial recognition and detection in ROS (Robot Operating System) applications.

A Jupyter Notebook library focused on making tensor manipulation and visualization more accessible to developers.

A curated list of awesome robotics-related foundation models and resources for developers.

A Python library for quickly editing and fine-tuning large language models like GPT, BLOOM, and LLAMA.

A collection of papers on the topic of Computer Vision in the Wild (CVinW)

An open-source, local version of the Tianruo OCR library that uses Chinese-lite and PaddleOCR frameworks for text recognition.

A tutorial for building Poe server bots using Python, focused on developers building AI tools.

A fast, extensible, and multi-threaded C# library that simplifies the development of Genetic Algorithm applications.

A real-time, single-stage face detection library with faster speed and higher accuracy.

An open-source toolbox for visual fashion analysis based on PyTorch, focused on tasks like attribute prediction and clothes retrieval.

This is a Lua library for building neural networks, a core component of deep learning frameworks.

A Python library for learning knowledge graph embeddings, useful for AI-powered discovery and recommendation systems.

A Python extension for the Stable Diffusion webUI that removes backgrounds from images.

Step-Audio 2 is an end-to-end multi-modal large language model for industry-strength audio understanding and speech conversation.

An implementation of a pose-guided text-to-video generation model using the LAION Pose Dataset.

A collection of GPT models and resources for developers interested in AI-powered coding tools and platforms.

This repository contains sample code and notebooks for the Gemini platform, a developer-focused AI tool ecosystem.

Demo of in-browser Fast Neural Style Transfer with deeplearn.js library

Pre-trained model for pitch estimation from audio, useful for music information retrieval tasks.

Infinite Bookshelf is a Python library that uses Groq and Llama3 to generate entire books in seconds.

A custom Home Assistant component that uses OpenAI to control devices, enabling conversational AI home automation.

A developer-friendly natural language processing library for building chatbots, extracting entities, and analyzing sentiment.

UNO is a universal customization method for both single and multi-subject image generation using diffusion models.

Nearest neighbor search library for high-dimensional data, useful for AI/ML applications.

BSRGAN is a PyTorch library for designing practical degradation models for deep blind image super-resolution.