Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

C/C++ development kit for Sipeed Maix ecosystem boards

Official comfyui repository of Hellomeme

M2dock开发板实现视频监控摄像头

Model for MDX23 music separation contest

Deezer source separation library including pretrained models.

GUI for a Vocal Remover that uses Deep Neural Networks.

[ICLR2025] DisPose: Disentangling Pose Guidance for Controllable Human Image Animation

Qt SerialPort-UDP-TCP-WebSocket-Modbus-CAN-BLE-Assistant.

This was part of graduation project done in zewailcity.the whole project included tracking and action detection

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

Unity plugin to run MediaPipe graphs

Voice data <= 10 mins can also be used to train a good VC model!

A cross platform audio library.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Source code of the paper Scene-Aware 3D Multi-Human Motion Capture, EUROGRAPHICS 2023

[ICCV 2023] StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces

Core library for CH32duino

Arduino Core for CH32V003 RISC-V microcontroller

TRACE is a tool that takes a single tennis match video feed and automatically extracts player, court, and ball information. The collected information allows us to see the top-view of the tennis mat…

NEW - YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite

Delicately-TUICed 0-RTT proxy protocol

Object Detection and Multi-Object Tracking

Image-to-Image Translation in PyTorch