LTX-2 Drops Full Open Weights and Training Code for Video Generation

A new open-source video generation model ships with complete weights, training code, and distilled variants — bringing local video generation closer to parity with proprietary tools.

LTX-2 has been released with full open weights, training code, and distilled models optimized for local inference, as @kimmonismus reported. The release is notable for its completeness: unlike many open-source model releases that ship weights without training code, LTX-2 gives the community everything needed to reproduce, fine-tune, and build on the work.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief