Realtime hand tracking and finger tracking in Unity using Mediapipe

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

H5 Page Maker, H5 Editor, LowCode. Make H5 as easy as building blocks. | 让H5制作像搭积木一样简单, 轻松搭建H5页面, H5网站, PC端网站,LowCode平台.

Context parallel attention that accelerates DiT model inference with dynamic caching

[WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.

笔戈公开抽奖算法项目源码

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

3D Model Viewer supporting glTF and 3D Gaussian Splats

Powerful web graphics runtime built on WebGL, WebGPU, WebXR and glTF

3D Gaussian Splat Editor

Dense Prediction Transformers

Automatic 2D-to-3D Video Conversion with CNNs

OCR, layout analysis, reading order, table recognition in 90+ languages

The best OSS video generation models

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Roo Code (prev. Roo Cline) is a VS Code plugin that enhances coding with AI-powered automation, multi-model support, and experimental features

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

DeepSeek LLM: Let there be answers

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

DeepSeek-VL: Towards Real-World Vision-Language Understanding

DeepSeek Coder: Let the Code Write Itself

Make websites accessible for AI agents

Talking Head (3D): A JavaScript class for real-time lip-sync using Ready Player Me full-body 3D avatars.

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

Arbitrary-steps Image Super-resolution via Diffusion Inversion

Voice activity detector (VAD) for the browser with a simple API