Lightricks (LTX) Open Models: Model List, Licenses and Articles

September 27, 2026

About Lightricks (LTX)

Lightricks is the company behind the LTX video generation models. On Hugging Face it runs the Lightricks organization under the name LTX.io and releases the LTX series there.

It is one of the leading publishers of video generation models you can run locally, and it stands out for releasing many official task-specific LoRAs in addition to the main models.

What It Releases

• LTX-2.5 (July 2026): a model that turns images and text into video; its Hugging Face tags also cover generating video with audio and generating audio from video. A diffusers version (about 19B) is also available.
• Official LoRAs: many control LoRAs (IC-LoRAs) for LTX-2.3 and 2.5, for camera motion, slow motion, cinemagraphs, colorization, deblurring, day-to-night conversion, upscaling and more. LoRAs are add-on components rather than models, so they are not listed in the table below.
• Earlier models include LTX-Video and LTX-2.

Licenses

The LTX-2 line uses its own LTX-2 Community License. Individuals and small organizations can use it broadly, but organizations with annual revenue of US$10 million or more (counting subsidiaries and affiliates together) need a paid license for any use other than non-commercial purposes. Most models require agreeing on Hugging Face before download. This summary is not legal advice; read the license text before use.

Running Them Locally

• There are no official GGUF builds (as of 2026-09-26). The models are tagged for ComfyUI, which is the usual way to run them.
• Video generation models load a text encoder and VAE besides the main model. Check the memory needed for all components in the tables in our articles.

Sources: the model list and model tags of the Lightricks organization on Hugging Face; the LTX-2 Community License (LICENSE-2_x) (all as of 2026-09-26).

Our Coverage and Data

Local Model Watch has published 1 article(s) on Lightricks (LTX)’s own models, 0 on third-party fine-tunes and quantized builds based on them, and 0 from its official blog. The model list below is collected by code from Hugging Face every day. Part of our publisher index; model families link to their family pages.

At a Glance

Recent Models on Hugging Face

The publisher lists 66 models in total on Hugging Face. Below are up to 15 of the most recent generative models (text, image, video, audio and so on), the scope of this site, per organization. Classifiers, feature extractors, research components and repositories without a model card are omitted, and the publisher’s own quantized builds and helper variants are folded into the row of the original model. Parameter counts are left blank for repositories that pack weights into integer types, where Hugging Face’s count is not the real parameter count.

From the Hugging Face API. Last changed 2026-09-27 (JST). Collected by code.

Licenses of Its Own Models (as recorded in our articles)

The license can differ from model to model even within one publisher. This is not legal advice; check each model’s license text before use.

By Model Family

Articles on Its Own Models

Last updated 2026-09-27 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under “Our Coverage and Data" are assembled by code from our article log and the Hugging Face API.