Lightricks/LTX-2

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

What it solves

LTX-2 is a foundation model designed to handle the complexities of modern video generation within a single system. It addresses the need for high-fidelity video that is synchronized with audio, providing a production-ready output that can be generated from text or images.

Related

  • Project
    james-see/ltx-video-mac

    A native macOS application for generating AI videos with synchronized audio from text or images using the LTX-2 model and MLX framework on Apple Silicon.

  • Project
    aigc-apps/VideoX-Fun

    A video generation pipeline supporting CogVideoX-Fun and Wan 2.1 models for text, image, and video-to-video generation with advanced structural and camera controls.

  • Project
    fudan-generative-vision/Hallo-Live

    Hallo-Live is a real-time text-driven framework that generates synchronized audio and video for digital avatars using a causal dual-stream Diffusion Transformer.

  • Project
    ModelTC/LightX2V

    A lightweight inference framework for efficient image and video generation that optimizes performance through quantization, distillation, and advanced parallelism.

  • Project
    Lightricks/ComfyUI-LTXVideo

    A collection of custom ComfyUI nodes and workflows that extend the LTX-2 video generation model with advanced control, HDR output, AI dubbing, and generative upscaling.