A feature-rich command-line audio/video downloader

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Official Code for DragGAN (SIGGRAPH 2023)

A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.

Generate 3D objects conditioned on text or images

3D Reconstruction Software

Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Stable Diffusion built-in to Blender

Official PyTorch implementation of StyleGAN3

小红书链接提取/作品采集工具：提取账号发布、收藏、点赞、专辑作品链接；提取搜索结果作品、用户链接；采集小红书作品信息；提取小红书作品下载地址；下载小红书无水印作品文件

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

Games: Create interesting games in pure python.

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

全自动录播、直播录制、分p投稿工具，支持twitch、ytb频道搬运。

Free Python Games

This repository provides motion datasets collected by Bandai Namco Research Inc

This is the Mov2mov plugin for Automatic1111/stable-diffusion-webui.

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

The code from my 12 hour live stream where I created a tower defense game with pygame.

A Blender add-on for building tile based low-poly scenes with paint/map editor like tools