Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

😼 优雅地使用基于 clash/mihomo 的代理环境

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

CUDA accelerated rasterization of gaussian splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

c++实现的sfrmat

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

(Deprecated) Python bindings for COLMAP

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

YOLOv5 ONNX Runtime C++ inference code.

MiniCPM on Android platform.

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

A community-maintained Python framework for creating mathematical animations.

✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

The reinforcement learning training code for AgiBot X1.

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Acconeer Exploration Tool

Official inference repo for FLUX.1 models

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Declarative visualization library for Python

Understanding Deep Learning - Simon J.D. Prince

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Create a draggable and resizable dashboard in Streamlit, featuring Material UI widgets, Monaco editor (Visual Studio Code), Nivo charts, and more!

A full-featured utility for managing Windows Subsystem for Linux (WSL)

Official Implementation for CVPR 2024 paper: CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor

Making binary mask images from JSON annotation

https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1

The Unreasonable Effectiveness of Synthetic Data