Connected components on discrete and continuous multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants; periodic boundaries (4, 8, & 6)

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

Wan: Open and Advanced Large-Scale Video Generative Models

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Official inference repo for FLUX.1 models

Fast and memory-efficient exact attention

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

Karras et al. (2022) diffusion models for PyTorch

Efficient vision foundation models for high-resolution generation and perception.

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

better multiprocessing and multithreading in Python

Repository for the Face Recognition Vendor Test (FRVT)

[CVPR 2025 Oral] VGGT: Visual Geometry Grounded Transformer

A comprehensive collection of IQA papers

OCR & Document Extraction using vision models

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Code for running RFdiffusion

A cool dock (desktop panel) for Linux desktop

Latte-Dock and WM status bar customization features for the default KDE Plasma panel

KDE Plasma6 widget with window controls

RTL8188FU driver for Linux 4.15.x ~ 6.8.x

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

🙌 OpenHands: Code Less, Make More

Robust recipes to align language models with human and AI preferences

Fully open reproduction of DeepSeek-R1