一个图像生成和编辑项目

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

Diffusers for Wan2.2

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline

Windows Cleaner——专治C盘爆红及各种不服！

real time face swap and one-click video face swap with only a single image. You can use one face or ten faces to replace in realtime using insightface, mouth mask, face tracking

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

GAG is a GUI for GPT-SoVITS inference. Just add it to the official integration package and run for a smoother experience.

Official implementation of "FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on"

The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization". ColorFlow：基于检索增强的图像序列上色

MSST-GUI is a Qt5-based inference GUI, designed to provide a convenient and intuitive way to inference (mainly for my own use)

The swiss army knife of lossless video/audio editing