# Run LTX-Video

Generates short video clips from a description or a still image. Ready in about 90 seconds on an L40S, from $0.89/hr. No install, no code.

## What it does

LTX-Video makes video from a written description, or animates a still image you already have.

It is the fastest open video model by a wide margin. Where most video models take several minutes for a few seconds of footage, this one is close to real time.

Clips are short, around five seconds, and quality is below what you would shoot. It is useful for backgrounds, transitions, motion tests, and social content, not for the hero shot.

## Your setup

We run LTX-Video on an L40S with 48GB of memory, at $0.89 per hour, billed by the minute. It takes about 25 seconds per clip.

Video models hold every frame of the clip in memory at once while they generate, so memory scales with clip length rather than with the size of the model. LTX-Video is only 2 billion parameters but a five second clip still needs about 20GB of working space. The 48GB L40S leaves room to push to longer clips and higher resolutions without the job failing partway.

## What it costs

100 clips takes about 42 minutes of GPU time, which is about $0.62.

## Two ways to run it

- **Open the app.** Type a description, generate, preview in the browser.
- **Run a batch job.** Generate many clips from a list of descriptions in one run.

## Model facts

| Field | Value |
|---|---|
| Parameters | 2B |
| License | LTXV Open Weights License |
| Memory required | 20GB minimum, 48GB recommended |
| Base model | Trained from scratch by Lightricks |
| Publisher | Lightricks |
| Recommended hardware | L40S, 48GB |
| Category | [Video and film](https://gpuvault.io/working-on/video-and-film/) |

## Questions people ask

### Do I need to install anything to use LTX-Video?

No. We start a machine with LTX-Video already loaded and hand you a link. Everything runs in your browser, there is nothing to download, and nothing is left on your computer afterwards. It works the same on a Mac, a Windows laptop, or a Chromebook. A workspace is usually ready in about 90 seconds.

### How much does it cost to run 100 clips?

About $0.62. LTX-Video takes about 25 seconds per clip on the L40S we recommend, so 100 clips is roughly 42 minutes of GPU time at $0.89 per hour. Billing is by the minute, and a batch job shuts the GPU off the moment the last item finishes. The calculator above works this out for your own numbers.

### Can I run LTX-Video on a cheaper card?

Sometimes, and the calculator will not always make it look worth it. Video models hold every frame of the clip in memory at once while they generate, so memory scales with clip length rather than with the size of the model. LTX-Video is only 2 billion parameters but a five second clip still needs about 20GB of working space. The 48GB L40S leaves room to push to longer clips and higher resolutions without the job failing partway. If you want to try a different card anyway, the advanced catalog lets you pick one and shows the estimated time before you commit.

### What are the license restrictions on LTX-Video?

LTX-Video is released under the LTXV Open Weights License. That is not a permissive license, so read it before you use the output in paid work. We show the license on every model page precisely because this catches people out, and there is usually a permissively licensed alternative in the same category.

### What happens to my files after I stop?

Anything you save into your workspace folder stays in your account and is there when you come back. Everything else is destroyed: the machine is terminated and its disk is wiped. Batch job inputs and outputs are deleted from our storage 24 hours after you download them. We do not read your files or use them to train anything.

### What if it fails partway through?

You are not charged for work that did not complete, and failed sessions are refunded automatically. Batch jobs write each output as it finishes rather than at the end, so a failure at item 380 of 400 leaves you 379 usable files and a message saying what broke. Restarting picks up where it stopped rather than redoing the work.

---

*Source: https://gpuvault.io/model/ltx-video/ — GPUVault, GPU rental by the minute.*