Trending Projects

StableAvatar is an end-to-end video diffusion transformer that generates high-quality audio-driven avatar videos.

A Python project that processes and renders neural networks to gain insights on model architecture and parameters.

A Python library for connecting Gaussian splatting and depth in computer vision tasks like monocular depth estimation and view synthesis.

A PyTorch library for implementing 2D Discrete Wavelet Transform and Dual Tree Complex Wavelet Transform, useful for vibe coders working with AI and signal processing.

A comprehensive collection of deep learning interview questions for developers building with AI tools.

KoGPT is a Korean language model based on GPT that can be used for natural language processing tasks.

Easy-to-use and powerful LLM and SLM library with awesome model zoo for natural language processing.

Generate 3D objects conditioned on text or images using a pre-trained AI model.

Databricks' Dolly, a large language model trained on the Databricks Machine Learning Platform

A Go package for computer vision using OpenCV 4 and beyond, with support for DNN, CUDA, and more.

A learning repository focused on AI tools, machine learning, and natural language processing for developers.

A community-maintained PHP API client that allows developers to interact with the OpenAI API.

Basic Machine Learning and Deep Learning library written in Python

Facilitates the design, comparison, and sharing of deep text matching models for NLP applications.

OpenVSLAM is a versatile visual SLAM framework for computer vision and robotics applications.

Efficient neural feature detector and descriptor for computer vision tasks.

LangChain Korean tutorials to help developers effectively use the LangChain framework for building AI-powered applications.

An open-source project that provides in-depth analysis of the source code and algorithms behind Spark's ML library.

Aimbot tool using AI and machine learning to improve aim in various video games.

This is the official implementation of Multi-Agent PPO (MAPPO), a reinforcement learning algorithm for multi-agent environments.

A common interface for building AI agents, tech stack agnostic and compatible with various AI frameworks and LLMs.

An AI-powered application platform that simplifies and optimizes the development of large language model-based applications.

A collection of NLP tutorials covering sentiment analysis, text classification, and neural machine translation.

An AI-powered markdown editor that lets developers leverage large language models with their documents, deployable locally or in the cloud.

An open-source speech recognition library for the Espressif ESP32 microcontroller platform.

A Python command-line client for the Whisper speech-to-text model by OpenAI, using the CTranslate2 library.

Dream 7B is a large diffusion language model that enables advanced AI-powered text generation and editing capabilities.

QPython is an Android Python engine focused on Python and AI learning with a range of features.

A fast and simple face swap extension node for the ComfyUI AI tool, built using Python.

Curated repository of papers and resources on multi-camera 3D object detection and segmentation in bird's-eye-view.

A library for accelerating deep neural networks through channel pruning, a model compression technique.

DynamicTanh (DyT) is a Python library that enhances the performance of neural networks by introducing a novel activation function.

Interactive image manipulation using GANs with drag-based controls

Curated list of top 100 deep learning papers (2012-2016) for developers

A fork of the so-vits-svc project with realtime support, improved interface, and more features for AI-powered voice conversion.

A fast, open-source library for time series forecasting using statistical and econometric models.

OpenHealth is an AI-powered health assistant that helps users manage their healthcare data.

A small package to create visualizations of PyTorch execution graphs for AI/ML developers.

CUDA Python: A library that brings the power of CUDA to Python, enabling high-performance GPU acceleration.

A comprehensive collection of interview questions and answers for AI, computer vision, and LLM topics.

A hub for EleutherAI's work on interpretability and learning dynamics for large language models.

A Python library for transcription, forced alignment, and audio indexing using OpenAI's Whisper model.

A Python library that helps developers extract structured data from tricky documents using vision-language models.

Generate music based on natural language prompts using local LLM models.

A CUDA-accelerated robotics library for motion planning and control using PyTorch.

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

A generative AI model for creating fashion designs and garments.

A simple PyTorch implementation of Generative Adversarial Networks for generating anime-style faces.

Comprehensive guide to learn Retrieval Augmented Generation (RAG) from basics to advanced.

A library for running TensorFlow on Arm-based devices like Raspberry Pi, enabling machine learning on edge devices.