How to run LTX Video 13B on ComfyUI (image-to-video)

LTX Video is a popular local AI model known for its generation speed and low VRAM usage. The LTXV-13B model has 13 billion parameters, a 6-fold increase over the previous 2B model. This translates to better details, prompt adherence, and more coherent videos.

In this tutorial, I will show you how to install and run the LTXV-13B img2vid on ComfyUI.

Table of Contents

Software
Improvement in LTXV 13B model
Alternative models
LTX Video 13B Image-to-video workflow
Reference

Software

We will use ComfyUI, an alternative to AUTOMATIC1111. You can use it on Windows, Mac, or Google Colab. If you prefer using a ComfyUI service, Think Diffusion offers our readers an extra 20% credit.

Read the ComfyUI beginner’s guide if you are new to ComfyUI. See the Quick Start Guide if you are new to AI images and videos.

Take the ComfyUI course to learn how to use ComfyUI step by step.

Improvement in LTXV 13B model

The LTXV 13B model is a huge step from the 2B model.

Higher quality: The quality of the 13B model is noticeably higher than the 2B model.
Speed is not bad: It takes under 3 minutes to generate a 4-second video on my RTX4090. It is slower than the 2B model, but it is still fast enough.

Alternative models

You may also consider the following models, which can turn an image into a video.

Wan 2.1 Video: A workhorse in local image-to-video
Hunyuan Video: Another high-quality choice
FramePack: long AI video with low VRAM
LTX Video 2B: The smaller version of LTXV. It is faster, but the quality is lower

LTX Video 13B Image-to-video workflow

Step 1: Download the workflow

Download the ComfyUI JSON workflow below.

Download

Drag and drop the JSON file to ComfyUI.

Step 2: Install missing nodes

If you see nodes with red borders, you don’t have the custom nodes required for this workflow. You should have ComfyUI Manager installed before performing this step.

Click Manager > Install Missing Custom Nodes.