Navigation2's dynamic obstacle detection, tracking, and processing pipelines.

PX4 Autopilot Software

[CVPR2024] GSVA: Generalized Segmentation via Multimodal Large Language Models

Tag manager and captioner for image datasets

[ICML'24 Oral] "MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions"

Implementation for MatMul-free LM.

Fast Multimodal LLM on Mobile Devices

Official Code for DragGAN (SIGGRAPH 2023)

Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

Python scripts for the Segment Anythin 2 (SAM2) model in ONNX

The entrance repository of Markdown presentation ecosystem

Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon

Use Florence 2 to auto-label data for use in training fine-tuned object detection models.

The official repo for "SpatialBot: Precise Spatial Understanding with Vision Language Models.

Strong and Open Vision Language Assistant for Mobile Devices

Compose multimodal datasets 🎹

GPT4V-level open-source multi-modal model based on Llama3-8B

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Webots Robot Simulator

Self-driving car simulator for the Duckietown universe

Traffic scenario definition and execution engine

Open-source simulator for autonomous driving research.

An open autonomous driving platform

The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

Shared data types for building collaborative software

This repository shows how to solve ONNX export issue in Segment Anything model

Images to inference with no labeling (use foundation models to train supervised models).

Vite & Vue powered static site generator.