Stars
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
Kernel module to evade KVM's detection through RDTSC timer
A patch to hide qemu itself, bypass mhyprot,EAC,nProtect / VMProtect,VProtect, Themida, Enigma Protector,Safegine Shielden
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
SoftVC VITS Singing Voice Conversion
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
使用盲水印保护创作者的知识产权using invisible watermark to protect creator's intellectual property
Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！
文本盲水印：把信息隐匿到文本中，put invisible blind watermark into a text.
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
StyleGAN - Official TensorFlow Implementation
DeepFaceLab is the leading software for creating deepfakes.
[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Denoising Diffusion Probabilistic Models
Generate 3D objects conditioned on text or images
An amazing manga comic colorization project | 漫画 AI 上色
Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。