Skip to content
OpenMicroDrama

Lightricks /ComfyUI-LTXVideo

Gives ComfyUI extra nodes and example workflows for the LTX-2 video model
ComfyUI workflowCustom licenseEnglish README
Open on GitHubSave
Stars
4.2k
30 days
New
Last push
today

About ComfyUI-LTXVideo

Adds extra nodes and ready-made workflows to ComfyUI for the LTX-2 video model. LTX-2 already ships in ComfyUI core, so these nodes add control, HDR, dubbing and upscaling. You get graphs for text-to-video, image-to-video, detail fixing, dubbing and text-to-audio. The catch: you need a CUDA GPU with 32GB+ VRAM and 100GB+ free disk space.

Best for: Teams running LTX-2 locally on a CUDA card with 32GB+ VRAM, for video, control, HDR or dubbing work.

What it does

  • Adds nodes under the LTXVideo category in the ComfyUI node menu
  • Ships example graphs for LTX-2.3, 2.5 and 2.0 text-to-video and image-to-video
  • Combines depth and edge control in one IC-LoRA (a small add-on model)
  • Converts SDR video to ACEScct HDR, with optional 16/32-bit EXR export
  • Dubs or rephrases speech and regenerates lips with the Dub-It IC-LoRA
  • Upscales video 2x or 4x with Pixel Spatial Upscaler IC-LoRAs

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Install ComfyUI and check you have a CUDA GPU with 32GB+ VRAM and 100GB+ free disk space.
  2. 2
    Open ComfyUI, press Ctrl+M, pick Install Custom Nodes and search for "LTXVideo".
  3. 3
    Click Install, wait for it to finish, then restart ComfyUI. Nodes show up under the LTXVideo category.
  4. 4
    Download the LTX-2.3 checkpoint into models/checkpoints, and the spatial and temporal upscalers into models/latent_upscale_models.
  5. 5
    Put the distilled LoRA and any IC-LoRAs in models/loras, and the Gemma 3 text encoder in models/text_encoders/gemma-3-12b-it-qat-q4_0-unquantized.
  6. 6
    Load a graph from ComfyUI/custom_nodes/ComfyUI-LTXVideo/example_workflows/; missing models download on first use.

Models and languages

Models it works with

  • LTX-2.3
  • LTX-2.5
  • LTX-2.0
  • Gemma 3

Interface and docs

  • English

Head-to-head

Alternatives

Other comfyui workflow projects people compare with ComfyUI-LTXVideo.

vrgamegirl19

comfyui-vrgamedevgirl

Plans, generates and fixes AI video scenes in ComfyUI

ComfyUI workflow
  • LTX 2.3
  • MiniMax H3
  • Z-Image
  • +2
740 GitHub starstodayCustom license

numz

ComfyUI-SeedVR2_VideoUpscaler

SeedVR2 video and image upscaling, as ComfyUI nodes or a CLI

ComfyUI workflow
  • SeedVR2 3B
  • SeedVR2 7B
2.9k GitHub stars9 months agoApache-2.0

kijai

ComfyUI-WanVideoWrapper

Puts WanVideo and related video models inside ComfyUI

ComfyUI workflow
  • Wan 2.1
  • Wan 2.2
  • SkyReels V2
  • +7
6.7k GitHub stars4 months agoApache-2.0

SegFault42

HeliosGen

AI image and video pipelines on a local node canvas

ComfyUI workflow
  • Veo 3.1
  • Kling 3.0
  • Seedance 2.0
  • +7
2.3k GitHub stars14 days agoNo license

Featured on OpenMicroDrama

Do you maintain ComfyUI-LTXVideo? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/lightricks-comfyui-ltxvideo)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 1, 2026. Covered by the LTX-2 Community License, not a standard open-source license. We write these descriptions ourselves. The repo's own docs are the final word.