LTX-Video
by Lightricks
LTX-Video is an open-source AI model that creates video from text prompts or still images, and can also extend or transform existing clips. It is aimed at people who want to generate video clips on their own hardware or through tools such as ComfyUI.
- Stars
- 11.3k
- Licence
- Apache-2.0
- Runs on
- A gpu machine, with a GPU
- Setup
- Technical
- Language
- Python
- Age
- 710 days
What you can do with it
- Turn a text description into a short video clip
- Animate a still image into a moving video
- Extend or transform an existing video using keyframes and control models such as depth, pose or edges
Make money with it
A freelancer could offer short AI-generated promotional videos or animated product images to small businesses as a paid service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Produce short social media or advert clips from product images without paying for a video stock library or an agency
- Create animated mock-ups and concept videos for client pitches at a lower cost
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
You install it as a Python project, download the model weights from Hugging Face, and run the inference script, or you can use it through ComfyUI or Diffusers.
Follow the official instructions in the project README.
Things to check
- Needs a powerful GPU with plenty of memory for the larger models
- The README says LTX-2 is now the main project, so this repository may receive fewer updates
- Generated video may raise copyright or likeness concerns, so check the model licence and your use case
Who's talking about it
Checked 01 Nov 2026. Summary drafted by AI from the project's README.
