Directory › Video › LTX-2
> GEM VIDEO · AUDIO & VOICE · LOCAL AI
LTX-2
by Lightricks
Lightricks' model that generates synchronized video and audio in a single pass.
View on GitHub →What it does
- Text or image to video with dialogue, sound effects and ambience
- Fast distilled pipeline, or slower "DFR" pipeline for final quality, up to 4K
- Free for organizations under $10M annual revenue (community license)
Install it
Requirements: Git, uv, a Hugging Face account (gated model, accept the terms).
Clone the repository
git clone https://github.com/Lightricks/LTX-2.git
Install dependencies
cd LTX-2 && uv sync --extra natten
Download the models (see README for the list)
https://github.com/Lightricks/LTX-2#-quick-start
The prompt for your agent
Paste it into your coding agent: it checks the requirements and installs it for you.
Claude CodeCodexCursorGemini CLIopencode
Prompt
Install LTX-2 (https://github.com/Lightricks/LTX-2) on my machine.
1. Check the requirements: Git, uv, a Hugging Face account (gated model, accept the terms). If anything is missing, tell me before installing anything.
2. Follow the official method:
- Clone the repository: git clone https://github.com/Lightricks/LTX-2.git
- Install dependencies: cd LTX-2 && uv sync --extra natten
- see https://github.com/Lightricks/LTX-2#-quick-start
3. Check that it works, then explain how to launch it and where to start.
Always review what your agent is about to run, especially install commands.