LTX-2.5 released on HuggingFace with text-to-video task
On HuggingFace, the model comfyicu/LTX-2.5 has been published with the text-to-video task. Publication date — 13.08.2026, the model has 3630 downloads. Details are on the model page.
What it means
Our reference of AI tools for 3D and video currently has no tool pages dedicated to text-to-video. The closest tools in topic are 3D generators: OpenLRM, Hunyuan3D 2.1 and TRELLIS. All of them solve the image-to-3d task, so comparing them directly with LTX-2.5 would be incorrect: this is a different class of tools.
The release of LTX-2.5 shows that text-to-video continues to evolve as a separate direction. Since the reference does not yet have a fact sheet for this model, we cannot assess its hardware requirements, license, or export formats based on our data.How the method works. The diagram is drawn based on this news note.
VoxelModel-v1: new open-source text-to-3d model on HuggingFaceThe bench-labs/VoxelModel-v1 model, which tackles the text-to-3d task, has been published on HuggingFace. The model appeared on July 26, 2026, and the…
SparsePR accelerates video generators with training-free sparse attentionResearchers introduced SparsePR, a training-free block-sparse attention method for video generators and world models. The paper was published on arXiv…
ROAD cuts the cost of 3D generation training by transferring knowledge from discriminative modelsThe authors of ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation propose a method that uses discriminative 3D m…
New h3-vbvr model on HuggingFace tackles image-to-videoOn August 18, 2026, the Patarapoom/h3-vbvr model was published on HuggingFace with the image-to-video task. At the time of publication, it had 2,434 d…