Practice Code for text to image trainer

This is the code for Mark Rober's Domino Robot project. You can find a bunch more info about the project, including details about the software architecture on my website.

A lightweight library for portable low-level GPU computation using WebGPU.

Brand new TTS solution

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

一款轻量级、高性能、功能强大的内网穿透代理服务器。支持tcp、udp、socks5、http等几乎所有流量转发，可用来访问内网网站、本地支付接口调试、ssh访问、远程桌面，内网dns解析、内网socks5代理等等……，并带有功能强大的web管理端。a lightweight, high-performance, powerful intranet penetration proxy serv…

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275+ supported cars.

World's fastest and most advanced password recovery utility

Grok open release

[CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

A static site generator for Swift developers.

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

🎨 数学公式识别增强版：中英文手写印刷公式、支持初级符号推导（数据结构基于 LaTeX 抽象语法树）Math Formula OCR Pro, supports handwrite, Chinese-mixed formulas and simple symbol reasoning (based on LaTeX AST).

Turn any glasses into AI-powered smart glasses

Vim-fork focused on extensibility and usability

A massively parallel, high-level programming language

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

[SIGGRAPH 2024] Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning

a custom comfyui node for fish-speech

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

macOS Touchpad and smooth scrolling support for ComfyUI

PuLID native implementation for ComfyUI

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

A family of diffusion models for text-to-audio generation.

Kolmogorov Arnold Networks

Official implement of ID-Aligner

PyTorch native finetuning library

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Azure / DeepSeek), Knowledge Base (file upload / knowledge manageme…