Store

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

AI-Powered Watermark Remover using Florence-2 and LaMA: Remove watermarks from images and videos, including AI-generated content from Sora, Runway, and others. Features a modern PyWebview GUI.

A real-time and multilingual speech translation model

Flask-based web UI for AI image/video generation, chat, and text-to-speech with queue management and multi-theme system

Flask-based web UI for AI image/video generation, chat, and text-to-speech with queue management and multi-theme system

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

Repository of AudioX

All-in-One

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

NSFW expansion module for ComfyUI Photoreal Prompt Builder

Inference server for MioTTS, a lightweight and fast LLM-based TTS model.

PyPi package for KaniTTS-2 model

dawproject-py – A Python repository with code for parsing, generating, and modifying DAWProject files, enabling seamless DAW interoperability.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Prebuilt DeepSpeed wheels for Windows with NVIDIA GPU support. Supports GTX 10 - RTX 50 series. Compiled with pytorch 2.7, 2.8 and cuda 12.8

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

they've simulated websites, worlds, and imaginary CLIs... but what if they simulated *you*?

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.