Public repository for Agent Skills

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

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

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

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

Let us control diffusion models!

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

GUI for a Vocal Remover that uses Deep Neural Networks.

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

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

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

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

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

基于vits与softvc的歌声音色转换模型

The PyTorch-based audio source separation toolkit for researchers

Graphormer is a general-purpose deep learning backbone for molecular modeling.

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

A recreation of Neuro-Sama originally created in 7 days.

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

A toolbox for skeleton-based action recognition.

Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination

Official implementation of "MeshDiffusion: Score-based Generative 3D Mesh Modeling" (ICLR 2023 Spotlight)

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (NeurIPS 2019)