AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.

A Fully Self-Hosted Solution for Full-Duplex Voice Interaction

An intuitive and low-overhead instrumentation tool for Python

For creating custom stickers for Arcaea and PJSK.

猜二次元角色

MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficienc…

GCCコンパイラーを可愛くしましょう！Make your GCC compiler kawaii.

Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Mamba SSM architecture

让你的 GCC 变得更可爱！

Unsupervised Learning for Image Registration

朋友圈转发截图生成工具（⚠️Fork 不是收藏，请勿在贡献代码以外的情况下 Fork！）

论文写作与资料分享

A hex editor for WeChat/QQ/TIM - PC版微信/QQ/TIM防撤回补丁（我已经看到���，撤回也没用了）

⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)

[AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

KikoPlay - NOT ONLY A Full-Featured Danmu Player 不仅仅是全功能弹幕播放器

No!! MeiryoUI is Windows system font setting tool on Windows 8.1/10/11.

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Easily train a good VC model with voice data <= 10 mins!

基于vits与softvc的歌声音色转换模型

An unprofessional open-source Chinese font derived from Fontworks' Klee One. 一款非专业的开源中文字体，基于 FONTWORKS 出品字体 Klee One 衍生。

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

Robust Speech Recognition via Large-Scale Weak Supervision

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism