LTX splits from Lightricks to build open world models for film, robotics, and beyond. 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. VP Land 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. VP Land 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 VP Land has 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.

LTX Trainer: 10 fine-tunable video effects, and the first agent-driven training loop. LTX just shipped a training framework, not a model. Ten demo LoRAs, open source, and the first time a major video lab has shipped a tool an agent can drive end-to-end, including the training step. Short version What to remember. * 01 LTX Trainer is a training framework, not a model: LoRAs and IC-LoRAs for video, audio, cross-modal, and reference-conditioned workflows * 02 10 demo LoRAs ship with the release (water simulation, ingredients, inpainting, day-to-night, colorization, instant shave, cross-eyed, deblurring, decompression), all trained on LTX-Video with the new trainer * 03 The first major video lab to ship a first-party agentic skill for training, not just prompting * 04 Open source: framework, IC-LoRAs, and the agentic skill are all on GitHub and HuggingFace * 05 Cost reality: pre-trained IC-LoRAs are free, but training a LoRA on a 19B base is hundreds to thousands of dollars in GPU time * 06 Two-layer choice: free IC-LoRAs + rented GPU for custom training, or skip training and pay per generation through a hosted route like fal.ai LTX just shipped a training framework, not a model. That distinction is the entire story, and most of the coverage is going to miss it. On June 17, 2026, Lightricks introduced LTX Trainer, a single framework for training LoRAs and IC-LoRAs across video, audio, cross-modal, and reference-conditioned workflows. Fully open source. GitHub, documentation, and HuggingFace all linked from the announcement. Ten demo effects ship with the release, all of them LoRAs the LTX team trained on top of LTX-Video using their own trainer. The ten effects, straight from LTX's launch thread. Each links to the demo video LTX posted: * Water Simulation. Add rivers, surf, rain, floods, or splashes to any shot while preserving composition and motion. https://x.com/ltx_io/status/2067284780081905685 * Ingredients. Combine characters, props, locations, and styles into fully realized video worlds generated from a reference sheet. https://x.com/ltx_io/status/2067284859668877723 * Inpainting and Outpainting. Extend and modify scenes beyond the original frame. https://x.com/ltx_io/status/2067284934847528965 * Day to Night. Transform daytime footage into nighttime scenes. https://x.com/ltx_io/status/2067285012060537021 * Colorization. Bring grayscale footage back to life. https://x.com/ltx_io/status/2067285088761708813 * Instant Shave. Remove facial hair while preserving identity and expressions. https://x.com/ltx_io/status/2067285165546873140 * Cross-Eyed. Make anyone go cross-eyed while keeping expressions, motion, and framing intact. https://x.com/ltx_io/status/2067285243690930534 * Deblurring. Turn blurry footage into sharp, clean video. https://x.com/ltx_io/status/2067285318454378784 * Decompression. Remove compression artifacts and restore visual quality. https://x.com/ltx_io/status/2067285396728521147 The tenth tweet is the closer, not a new effect: "All trained with LTX Trainer. What will you build?" https://x.com/ltx_io/status/2067285408468337046 (All nine demo videos are LTX's own assets, linked back to the original tweets. If a video breaks, the tweet is the source of truth.) What actually changed. First, the trainer is a framework, not a single skill. It supports video, audio, cross-modal, and reference-conditioned workflows in one place. That means a LoRA you train can be conditioned on a reference image, a reference video, an audio track, or a combination. Most of the existing video model ecosystem is still one-input, one-output. Multi-modal conditioning at the training stage is a real shift. Second, the open-source IC-LoRAs ship with the framework. IC-LoRA, in LTX's vocabulary, is in-context LoRA: the LoRA is conditioned on a reference input at inference time, so a single trained adapter can produce different outputs depending on the reference you feed it. The Ingredients effect (number 2 above) is the cleanest demonstration of the pattern. The LoRA turns a single reference sheet of characters, props, and locations into fully realized video worlds. Third, and the one most people will gloss over: a new agentic skill ships alongside the trainer. The line is buried in the announcement copy, but it is there. "Plus: new agentic skill, flexible conditioning, free IC-LoRAs, fully open source." The agentic skill is what lets an AI agent, not a human in a CLI, drive the training loop. Pick the base model, point it at a dataset, configure conditioning, kick off training, evaluate the output. That is the same shape as Scopeful's own MCP server surface, and it is the first time I have seen a major video lab ship a first-party agent surface for training rather than only for prompting. Why this matters if you are not a researcher. The reason I am writing this on Scopeful, where the beat is pricing and tooling, is that the gap between "an open-source trainer exists" and "you can actually use it" is enormous, and LTX is one of the few teams actually closing it. Most open-source video training setups require you to wire together the base model, the training loop, the conditioning pipeline, and the inference harness yourself. LTX Trainer ships all four as one project. The free IC-LoRAs are reference adapters you can download from HuggingFace, run locally, and use without retraining. The agentic skill exists so an agent, Claude, GPT, whatever you run, can use the trainer the same way it uses any other tool. That is the part with real Scopeful relevance. Scopeful has been saying for a year that the agent layer is the most underexplored surface in creative AI. Most vendors are still shipping prompt UIs. LTX just shipped a tool that an agent can drive end-to-end, including the training step. If the trend holds, every video model lab is going to ship an agent surface within twelve months, and the ones that ship it first will define what "agent-friendly" means in the category. The cost reality. The training framework itself is free and open source. The compute is not. A LoRA fine-tune on a 13B-to-19B parameter video model is not a laptop job. You are looking at a multi-GPU box or a cloud rental, and depending on the dataset size and target rank, the bill lands somewhere between a few hundred and a few thousand dollars per adapter. The 10 LTX-shipped IC-LoRAs save you that cost, because you can download and use them directly. The 11th adapter, the one you train on your own footage, is where the cost lives. If you do not want to train anything, the underlying LTX-Video model is also billable through hosted inference, including via fal.ai, which is what the Scopeful calculator already prices out. The LTX-2 family and the LTX 2.3 family are both in the catalog with per-second pricing. So you have a clean two-layer choice: use a pre-trained IC-LoRA from HuggingFace for free, train your own on rented GPUs, or skip training entirely and pay per generation through a hosted route. What I would actually do. If you are curious, the move is to grab the free IC-LoRAs from HuggingFace and try the Ingredients reference-sheet workflow first. It is the most generally useful of the ten, and the demos are convincing. Pair it with an LTX-Video inference route, either the open-source weights locally or a hosted route, and you can do reference-conditioned video generation today, on a laptop, for the cost of inference only. If you have a use case the free adapters do not cover, train your own. The trainer is the right primitive for that. Budget realistically: a single LoRA on a 19B base is a meaningful spend. Treat it like hiring, not like a subscription. And if you are building an agent that touches video models at all, watch LTX's agentic skill carefully. It is the first time a major video lab has shipped a tool designed to be driven by an agent, not by a prompt. That is the move the rest of the category is going to make, and the projects that adopt the pattern early are the ones that will set the standard. Links. * LTX Trainer GitHub: https://github.com/Lightricks/LTX-Trainer * LTX Trainer documentation: https://docs.ltx.io * LTX IC-LoRAs on HuggingFace: https://huggingface.co/Lightricks * LTX Studio on Scopeful: /tools/ltx-studio * The 10 demo effects, with videos, live in the launch thread: https://x.com/ltx_io/status/2067258965369528397 Scopeful tracks where creative-AI pricing moves, every week. If you would rather see a new model on the day it ships than the week after, the newsletter is for you. Questions & answers. * Is LTX Trainer free? - The framework is free and open source, and the IC-LoRAs that ship with it are free to download from HuggingFace. The cost of training your own LoRA on top of LTX-Video is the GPU time, which is hundreds to thousands of dollars per adapter on rented hardware depending on rank and dataset size. * What is IC-LoRA? - IC-LoRA, in LTX terminology, is in-context LoRA. The LoRA is conditioned on a reference input at inference time, so a single trained adapter can produce different outputs depending on the reference image, video, or audio you feed it. The Ingredients effect in the LTX Trainer launch thread is the clearest demonstration: one reference sheet becomes a fully realized video world. * Do I need to train a LoRA to use LTX Trainer? - No. The ten demo IC-LoRAs (water simulation, inpainting, day-to-night, colorization, and so on) are free to download and use. Train your own only if you have a use case the pre-trained adapters do not cover. * What is the new agentic skill? - A first-party agent surface that lets an AI agent, not a human in a CLI, drive the LTX Trainer training loop end-to-end: pick the base model, point at a dataset, configure conditioning, kick off training, evaluate the output. It is the first time a major video lab has shipped this kind of surface for training rather than only for prompting.