Lightricks releases LTX-2.5 with image-to-video task

Lightricks has published the LTX-2.5 model on HuggingFace for the image-to-video task. The publication is dated 23.07.2026, and the model has 39 downloads and 124 likes. The code is available as open source, with details on the model page.

What it means

LTX-2.5 handles the image-to-video task, meaning it animates a static image. In our reference on AI for 3D and video, Lightricks tools are not yet listed, and the closest tool pages in spirit are 3D generators with the image-to-3d task: OpenLRM, Hunyuan3D 2.1, and TRELLIS. These are a different class of tasks: they turn an image into a 3D object rather than a video, so LTX-2.5 does not directly overlap with them. Still, the release of an open-source model from Lightricks expands the landscape of tools that take an image as input and produce a moving result. For users choosing between generating a 3D asset and animation, this is another option in a related niche. The developer does not specify technical requirements, model weights size, or licenses for LTX-2.5 on the model page. It is too early to say whether LTX-2.5 will earn a place in the CPU3D reference: that requires data on licenses, hardware requirements, and output formats, none of which are present in the publication.