OpenMMLab Detection Toolbox and Benchmark

Effortless data labeling with AI support from Segment Anything and other awesome models.

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

Must-have resource for anyone who wants to experiment with and build on the OpenAI vision API 🔥

Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]

A tab for sd-webui for replacing objects in pictures or videos using detection prompt

A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.

Securade.ai HUB - A generative AI based edge platform for computer vision that connects to existing CCTV cameras and makes them smart.

Grounded Tracking for Streaming Videos

GroundedSAM Base Model plugin for Autodistill

Low-latency ONNX and TensorRT based zero-shot classification and detection with contrastive language-image pre-training based prompts

SegMate: A Segmentation Toolkit

Generative AI based image editing/inpainting made super easy to work with.

Grounding DINO module for use with Autodistill.

A simple demo for utilizing grounding dino and segment anything v2 models together

Explore the cutting edge of computer vision with this comprehensive repository, showcasing a spectrum from classical machine learning to state-of-the-art transformer models.

The Drowsiness Detection System uses YOLOv8 models to monitor drowsiness in real-time by detecting eye states and yawning. Built with Python and leveraging the GroundingDINO library for bounding box generation, this project offers real-time alerts through a PyQt5 interface.

[ArXiv2024] ModPrompt: Visual Modality Prompt for Adapting Vision-Language Object Detectors

Combining three computer vision foundation models, Segment Anything Model (SAM), Stable Diffusion, and Grounding DINO, to edit and manipulate images.