This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Rembg is a tool to remove images background

[ICCV 2025] Official Implementation of Contrastive Flow Matching

An MIT License of YOLOv9, YOLOv7, YOLO-RD

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

🚀 The fast, Pythonic way to build MCP servers and clients.

Easy Docker setup for Stable Diffusion with user-friendly UI

Project documentation with Markdown.

User manual written in markdown with HTML and PDF view

A GraphQL library for Python that leverages type annotations 🍓

Unofficial Amazon Cognito Identity Provider Dart SDK, to easily add user sign-up and sign-in to your mobile and web apps with AWS.

🚀 The easiest way to automate building and releasing your iOS and Android apps

Latest Evaluation Toolkit (LatestEval). Assessing the language models with latest, uncontaminated materials.

Open-source vector similarity search for Postgres

PyPika is a python SQL query builder that exposes the full richness of the SQL language using a syntax that reflects the resulting query. PyPika excels at all sorts of SQL queries but is especially…

Heron is a library that seamlessly integrates multiple Vision and Language models, as well as Video and Language models.

This is an unofficial implementation of the paper "Towards Total Recall in Industrial Anomaly Detection".

Create a TypeScript Action with tests, linting, workflow, publishing, and versioning

Actions for running CodeQL analysis

An open source implementation of CLIP.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

CUDA Templates for Linear Algebra Subroutines

Compare neural networks by their feature similarity

This is an unofficial implementation of the paper "Sub-Image Anomaly Detection with Deep Pyramid Correspondences".

Label-Efficient Semantic Segmentation with Diffusion Models (ICLR'2022)

Noise Conditional Score Networks (NeurIPS 2019, Oral)

Denoising Diffusion Implicit Models

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)