Radar

A simple face swapper based on insightface inswapper

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

Btw the name you should understand the purpose :) .

OpenGame: Open Agentic Coding for Games

The app lets you type any question or request and receives a detailed, reasoned answer from a powerful language model. You can adjust the system prompt and generation settings (max tokens, temperat...

LoRA Manager for ComfyUI - A powerful extension for organizing, previewing, and integrating LoRA models with metadata and workflow support.

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

A repository of well documented easy to follow workflows for ComfyUI

Faster Whisper transcription with CTranslate2

🔊 Generate high-quality, realistic speech with LuxTTS, a lightweight text-to-speech model for fast voice cloning and clear audio output.

FastAPI server docker for MiraiTTS - Adjusted for German language Sentence splitting

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

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

MoCha: End-to-End Video Character Replacement without Structural Guidance

This is the official implementation of our paper: "MiniMax-Remover: Taming Bad Noise Helps Video Object Removal"

[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

Xkaliber Agent is a powerful, autonomous AI interface built on Electron. It goes beyond standard chat by allowing local Ollama models to autonomously manage your file system, interact with APIs, and control physical robotics via GPIO. It features offline text-to-speech, multimodal vision, WhatsApp integration,

自动优化seedance-1.0-pro提示词根据官方docs，一键生成无水印视频

:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more. Features: Generate Text, MCP, Audio, Video, Images, Voice Cloning, Distributed, P2P and decentralized inference

Inpaint anything using Segment Anything and inpainting models.