We write your reusable computer vision tools. 💜

Create shapes that follow a spline path. Import background image, edit splines, and export for use in VACE.

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

Continuing to develop my program for the Elegoo SmartCar v4 using the Elegoo Smartcar Shield v1.1 and an Arduino Uno R3.

Software for my ELEGOO Smart Robot Car Kit V3.0 and V4.0

GLOMAP - Global Structured-from-Motion Revisited - Detailed Windows Install & Usage Instructions

CUDA accelerated rasterization of gaussian splatting

The python library for real-time communication

Tutorial to use Singstar Creator to create a PS2 Singstar DVD/iso from Ultrastar songs. Includes download for Singstar Creator.

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

Press shortcut → speak → get text. Free and open source. More local-first apps soon ❤️

Use Google's text-to-speech and speech-to-text models to talk to your PDF files, both text to audio and audio to audio.

Chat with GPT LLMs over voice, UI & terminal, all with access to the internet. Powered by OpenAI.

Fully open reproduction of DeepSeek-R1

🙌 OpenHands: AI-Driven Development

LlamaIndex is the leading framework for building LLM-powered agents over your data.

An extremely fast Python package and project manager, written in Rust.

Display and control your Android device

A simple module for fixing the vertical position of Streamlit containers relative to viewport instead of page or content

Full python interactive 3D Gaussian Splatting viewer for real-time editing and analyzing.

Kotlin Multiplatform Music Downloader, Supports Spotify / Gaana / Youtube Music / Jio Saavn / SoundCloud.

Simple, unified interface to multiple Generative AI providers

[CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference ima…

A low-power E-Paper weather display powered by an ESP32 microcontroller. Utilizes the OpenWeatherMap API.

Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal is…

Ultralytics YOLO 🚀