Official implementation of Log-linear Sparse Attention (LLSA).

DDT: Decoupled Diffusion Transformer

[CVPR 2025 Oral] Alias-free Latent Diffusion Models (official implementation)

[SIGGRAPH Asia 2025] Official code for "Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models."

Sample code for the book "Introduction to 3D Game Programming with DirectX 12"

collection of diffusion model papers categorized by their subareas

樱之刻简中汉化

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

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

A curated list of recent diffusion models for video generation, editing, and various other applications.

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

Demos for deep learning

A technical report on convolution arithmetic in the context of deep learning

Make FC(NES) Emulator Step-by-Step 一步一步模拟红白机

[T-ITS 2023] PanoFlow: Learning Optical Flow for Panoramic Images

微信公众号公式编辑插件

Seamless operability between C++11 and Python

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

An advanced monster manual for Tower of the Sorcerer.

OpenMMLab Pre-training Toolbox and Benchmark

OpenMMLab Model Deployment Framework

Tower of the Sorcerer for Windows Kai (改): Modifier of game variables and improvement of game experience

OpenMMLab Model Compression Toolbox and Benchmark.

Open-source simulator for autonomous driving research.

[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

OpenMMLab's next-generation platform for general 3D object detection.