Skip to main content
LTX-Video is a very efficient video model by lightricks. The important thing with this model is to give it long descriptive prompts.
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Multi Frame Control

Allows you to control the video with a series of images. You can download the input images: starting frame and ending frame. LTX-Video Multi Frame Control
Drag the video directly into ComfyUI to run the workflow.

​
Image to Video

​
LTXV Image to Video

Generate videos from still images. LTXV Image to Video workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “LTXV Image to Video” in Template Library
Input materials Upload this file to the matching LoadImage node:

ltxv_image_to_video_input_image.jpg

LoadImage node 78 · ltxv_image_to_video_input_image.jpg
ltxv_image_to_video_input_image.jpg
Drag the video directly into ComfyUI to run the workflow.

​
Text to Video

​
LTXV Text to Video

Generate videos from text prompts. LTXV Text to Video workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “LTXV Text to Video” in Template Library
Drag the video directly into ComfyUI to run the workflow.

​
Requirements

Download the following models and place them in the locations specified below:

ltx-video-2b-v0.9.5.safetensors

Download and place in ComfyUI/models/checkpoints/

t5xxl_fp16.safetensors

Download and place in ComfyUI/models/text_encoders/