How to Use LTX-Video to Generate Video Clips From Text
LTX-Video is a DiT-based open-weights text-to-video model from Lightricks that generates short clips (typically 2 to 5 seconds) from a text prompt, and it can run on a single consumer GPU if you use a quantized build. You install it through the ltxy package or the ComfyUI node, load a checkpoint, type a prompt, and export an MP4.
This guide walks through the practical setup on a machine with an RTX 3060 12GB, the settings that actually change output quality, and where LTX-Video stops being the right choice.
What is LTX-Video?
LTX-Video is a latent diffusion transformer that outputs video frames directly. Unlike older pipelines that generate frames one at a time and stutter, it denoises the whole clip together, which keeps motion coherent across the sequence.
The base model handles 768×512 at around 24-30 fps for a few seconds. There is a 0.9.x line with distilled variants that cut steps down to 8, so a 5-second clip can finish in under a minute on a mid-range card.
Is LTX-Video free to run?
Yes, the weights are open. You download them once and generate as much as your GPU allows. There is no per-second billing on the local route.
If you skip local hardware, hosted endpoints charge per second of video. Expect roughly $0.10 to $0.30 per generated 5-second clip depending on resolution. For anything past a few test clips a day, local is cheaper after the first month.
How do you install LTX-Video?
The fastest path on Windows or Linux is the ComfyUI node. Two steps get you to a working graph.
- Clone the LTX-Video ComfyUI nodes into your custom_nodes folder and restart ComfyUI.
- Drop the model checkpoint into models/checkpoints (the distilled fp8 file is about 8 GB).
- Load the example workflow, replace the text field with your prompt, and set frames to 121 (roughly 5 seconds at 24 fps).
- Click Queue. First run downloads the text encoder if it is missing.
For a pure Python route, install the inference package and run the bundled CLI script. It expects a CUDA 12.x build and about 16 GB of VRAM at fp16. On a 12GB card you want the fp8 checkpoint plus sequential CPU offload, which trades maybe 40 percent speed for fitting in memory.
What settings actually matter?
| Setting | Effect |
|---|---|
| Frames | 121 frames equals about 5 seconds; more frames means more VRAM |
| Steps | Distilled models look fine at 8; base needs 20-30 |
| CFG scale | Keep near 3 for distilled, 6-8 for base |
| Resolution | 768×512 is the sweet spot; 1216×704 needs a 24GB card |
Prompt structure helps more than knobs. Describe subject, action, camera, and lighting in that order. “A red fox trotting through snow, slow dolly-in, overcast light” beats a wall of adjectives.
Where does LTX-Video fall short?
Text rendering inside video is unreliable, so do not plan on captions baked into the footage. Hands and fast lateral motion still smear occasionally. And clips are short by design; stitching five-second segments into a minute-long scene creates visible seams unless you keep the camera locked.
If you need 30-second continuous shots or precise character consistency, a hosted model with longer context is a better fit. LTX-Video shines for b-roll, concept tests, and social loops where a few seconds is the whole deliverable.
Quick Summary
- LTX-Video is an open-weights text-to-video model that generates 2-5 second clips from text.
- It runs locally on 12GB of VRAM with the fp8 checkpoint, or via paid hosted APIs at roughly $0.10-$0.30 per clip.
- Distilled builds need only 8 steps, so short clips render in under a minute on mid-range GPUs.
- It is best for b-roll and concept loops, not long continuous scenes or on-screen text.
