LTX is spinning off from Lightricks to operate as an independent company built around open "world models," AI systems designed to understand and simulate physical and virtual environments. The move separates the AI foundation-model business from the consumer app maker that incubated it.
Zeev Farbman continues as LTX's co-founder and CEO, taking the founding team with him. Lightricks keeps its consumer mobile apps, including Facetune, under general manager Asaf Porat. LTX's models stay open, with weights and code available for companies to run, fine-tune, and deploy on their own hardware.
An open-model business splits off from a consumer app company
According to LTX's announcement, the spinoff formalizes a split that had been building inside Lightricks. The company behind Facetune had also become one of the more active releasers of open video models, and those two audiences, phone-app consumers and enterprise AI developers, want different things.
LTX now positions itself as a foundation-model company serving enterprises, studios, researchers, and developers. Lightricks stays focused on the mobile creativity apps that built its consumer base.
LTX-2 traction gave the split a business case
The spinoff arrives on the back of measurable adoption. LTX says its models have passed 22 million downloads on Hugging Face, making LTX the top open model on the platform since LTX-2 launched in January 2026.
We covered LTX-2.3's release, the current generation. It's a 22-billion-parameter model that pairs a 14-billion-parameter video stream with a 5-billion-parameter audio stream, generating synchronized 4K audio and video in a single pass at up to 50 frames per second. LTX says the model runs at roughly a tenth the render time and an eighth the cost of comparable systems.
That open, low-cost positioning has been consistent. We previously reported on LTXV breaking the 60-second barrier for long-form generation, and on LTX Desktop bringing local generation to consumer GPUs.
"World models" points the company past video
The rebrand signals ambition beyond text-to-video. LTX frames world models as a general-purpose engine for simulating physical reality: generating environments that carry an understanding of physics, predicting how objects move, how forces interact, and how scenes evolve over time.
That framing puts LTX in the same category as other open real-time world models we've tracked, including Skywork's Matrix-Game 3.0. The target markets LTX names reach well outside entertainment: film and gaming, but also robotics, manufacturing, autonomous vehicles, construction, warehouse automation, and space exploration.
What filmmakers actually get
For production teams, the near-term product lineup is unchanged by the corporate restructuring. LTX still ships the same access paths:
Open weights with a commercial license for on-premise deployment
API access through a managed console for teams that don't want to run their own infrastructure
LTX Studio, the production interface where features like Retake let editors adjust specific sections of a rendered shot
LTX Desktop for local generation on a single GPU
The open-weights commitment matters most for studios weighing where their footage goes. As proprietary video models from larger labs get more capable and more closed, LTX is betting that studios and enterprises will pay for models they can host, fine-tune, and keep in-house rather than route footage through an external API.
A standalone company with a wider mandate
Structuring LTX as its own company gives it a cleaner story for enterprise customers and investors than a video-model team living inside a consumer app maker. The consumer apps and the foundation models now report to different leaders with different roadmaps.
For filmmakers using LTX today, nothing breaks. What's less certain is whether "world models" becomes tooling that on-set and post teams can use the way LTX's video models already have, or stays a research-stage pitch aimed at robotics and industrial customers.
