Apps

Suno-style web UI for a self-hosted MiniMax-Music3 inference server

Image to video, your lora + CivitAI, stitching, cost readout

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

Reconstruct 3D Gaussian Splatting worlds from video using non-rigid alignment. Supports fast and extensive modes with 2DGS/3DGS rendering. https://github.com/lukasHoel/video_to_world

Generate audiobooks from e-books

DeepLiveCam PRO - Real-time face swap and one-click video deepfake. Commercial version.

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.

Password-locked file browser for every drive on this machine.

A local prompt-writing assistant for Ideogram 4, MiniMax H3 video, and plain-text image models, powered by a local LLM (llama-server).

Process text and images with GGUF LLMs in ComfyUI using llama.cpp, including Qwen3-VL, Qwen3.5, Qwen3.6, Qwen3.7, Qwen3.8, Gemma 4, and gpt-oss

AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]

🌍 Capture speech, translate it instantly, and playback audio in a selected language with this easy-to-use real-time voice translator built on Python and Streamlit.

Offline Vietnamese text-to-speech (TTS) and voice cloning - fully local on your own NVIDIA GPU (works on 4GB VRAM), no internet, no API keys. Clean web UI + CLI. Built on OmniVoice/KhanhTTS. | TTS tiếng Việt + clone giọng, chạy offline 100%.

Chinese sentence-based video clipping with FunASR

Contribute to onurburak9/Qwen3.8-27B-Uncensored-MLX development by creating an account on GitHub.

CapCap is a Windows desktop app for short-form video localization and dubbing. It brings transcription, translation, subtitle styling, voice generation, timeline editing, preview, and export into a single project workflow for Vietnamese-focused content production.

ComfyUI custom node for MiniMax H3 prompt synthesizing with interactive web tools & safe image upload.

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

seed-vc voice conversion adapted for Maestro (GPL-3.0). Cloned automatically at install time by github.com/Blizaine/Maestro - not for standalone use.