LTX-Video: video generator — what it does and what you need to run it

LTX-Video is an open source video generator from Lightricks that tackles the image-to-video task. The tool lets you turn a static image into a video clip, with the option of running it locally on your own hardware.

What it does

The authors position the model as a solution for generating video from an image (image-to-video). The repository tags also mention text-to-video and image-to-video-generation tasks, indicating support for text descriptions as an additional condition. The underlying architecture is based on diffusion-models and dit, the code is written in Python and integrated with the diffusers library.

What you need to run it

The code is open source under the Apache-2.0 license, while the model weights are distributed under a license the developers label as "other". The largest weight file is 26.6 GB, and the total size of all weight files is 236.4 GB.

As described by the author, the tool requires 1 GB of VRAM — verbatim: "Requires only 1GB of VRAM". MPS support on macOS with PyTorch 2.3.0 is declared. The codebase was tested with Python 3.10.5, CUDA 12.2, and supports PyTorch versions no older than 2.1.2. The repository was created in November 2024, with the latest code change dated January 2026.

Who it suits

The tool is aimed at those ready to run it locally and who have enough disk space to store the weights. The stated 1 GB VRAM requirement makes the model accessible to a wide range of GPUs, including relatively old or low-power cards. MPS support allows it to run on Mac computers with Apple Silicon.

It will not suit those looking for a cloud service without the need for a local installation — LTX-Video requires self-deployment from the repository. For users without experience with Python and the command line, the entry barrier may feel high.

The model and code are available on GitHub and Hugging Face, and additional information can be found on the project website. Since the weights license is marked as "other", it is worth carefully reviewing the terms before commercial use.