Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Reference PyTorch implementation and models for DINOv3

The official implementation of AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

PyTorch Implementation of the Paper 'AnyAnomaly': Official Version

This is the official repository for our recent paper "Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models".

The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"

An open source implementation of CLIP.

[CVPR 2025] The official implementation of “UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection”

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Official implementation for AnomalyCLIP (ICLR 2024)

The Codes and Data of A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection [ICLR'25]

Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch

[CVPR 2025] UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".

ADer (https://arxiv.org/abs/2406.03262) is an open source visual anomaly detection toolbox based on PyTorch, which supports multiple popular AD datasets and approaches.

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

[AAAI-2024] Offical code for <Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt>.

A Collection of Variational Autoencoders (VAE) in PyTorch.

[CVPR 2023] Unofficial re-implementation of "WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation".

Let us control diffusion models!

[AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.