Async I/O framework for Zig

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

A C client for NATS

Go SDK for CloudEvents

Taming Stable Diffusion for Lip Sync!

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的mcp框架。

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

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

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

Industry leading face manipulation platform

Containers for machine learning

Swap faces in pictures

real time face swap and one-click video deepfake with only a single image

one-stop telemetry collector for nightingale

Full Text Search Engine - built for Hackers not Hyperscalers

Wombat

Redpanda is a streaming data platform for developers. Kafka API compatible. 10x faster. No ZooKeeper. No JVM!

Concurrent data structures for Go

Hierarchical timing Wheel For Go, Manage Millions of timers with O(1), Operations.

Everything required to run your own Base node

Lightpanda: the headless browser designed for AI and automation

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

Wan: Open and Advanced Large-Scale Video Generative Models