Lightricks just made AI video generation 30x faster — and you won’t need a $10,000 GPU
1 min read
Summary
Lightricks, the company behind apps including Facetune and VideoLeap, has launched its most powerful AI video generation model to date, LTX Video 13-billion parameter (LTXV-13B).
LTXV-13B generates professional-quality AI video up to 30 times faster than comparable models, and is intended to be operated on consumer-grade hardware rather than expensive enterprise GPUs.
The model uses a technique called multiscale rendering, which generates video in progressive layers of detail, enabling creators to produce content more quickly and on standard desktops or high-end laptops.
LTXV-13B is available as an open-source release, and is being integrated into Lightrick’s LTX Studio platform.
The company plans to monetise the model through licensing agreements with larger enterprises generating over $10m in revenue.