AI video company Lightricks is stepping up its game for professional content creators with a significant update to its LTX Video model, giving users the option to create up to 60 seconds of videographic content in one go.
The company says LTXV is the first long-form AI video generation model that’s been made available to the public, with the length of its videos far exceeding the industry standard of just eight seconds. Rather than making short and sweet video clips, creators now have the ability to create much harder-hitting, one-minute-long stories with nothing more than natural language prompts.
Lightricks, which used to be laser-focused on consumer use cases with its visual content mobile applications like Videoleap and Facetune, underscores its pivot to professional content creators with another game-changing feature in the new AI model update.
In addition to longer-form videos, the company has also made LTXV the first streaming-capable model of its kind, and even better, it provides users with the ability to direct their videos in real-time by adding new prompts at different points along the video’s timeline. This change makes for unprecedented control over the content that people create.
Lightricks co-founder and CEO Zeev Farbman believes that these two new capabilities set the model apart, with users able to manipulate longer video sequences for the first time. The new version of LTXV enables “coherent storytelling with visual and semantic consistency, transforming AI video from a demo or just some random clip into a true medium with creative intent,” he said in a statement.
Also Read: In the Age of AI, Trust Is the Real Infrastructure
The enhanced, real-time creation controls are made possible through Lightricks’ newly improved autoregressive video engine. After the first second of the user’s long-form AI video is generated, they can immediately enter additional prompts to adapt its output on the fly, evolving the scene to meet their creative vision. As each batch of video frames is generated, these “condition” the next batch of frames, ensuring continuity and consistency as the longform content is generated and streamed in real-time.
Such capabilities were conceived to open the door to the idea of generative storytelling and continuous narratives, according to the company’s announcement.
Professional Video Creation
Use cases for the new LTXV long-form video capabilities are numerous. Social media influencers and ad studios can use it to generate vertical ads on demand. There are also new possibilities in video games, as the model can allow developers to quickly create live-rendered cutscenes in games, based on the user’s actions taken during gameplay.
Other use cases include augmented reality applications, with AI-generated characters appearing alongside human performers, synced with their real-time actions, and educational content that evolves in real-time, based on the inputs of learners.
This direction aligns well with Lightricks’ growing belief that businesses are going to be increasingly interested in using – and paying for – AI applications as the technology evolves and becomes more powerful. The company first began playing around with AI within its fun, smartphone-based apps.
Lightricks subsequently went all-in on AI technology with the launch of LTX Studio in 2023, targeting a very different audience in advertising production teams, product marketers and aspiring filmmakers with professional-grade creation tools for generating storyboards, pitch decks and even production-ready footage.
LTX Studio is a subscription-based platform that dramatically enhances the basic capabilities of the LTXV model. It’s a suite of editing tools that creators can use to apply extensive project-level and shot-level controls to their AI-generated content and transform it into slick, professional-looking videos without investing in a film studio and human actors. It includes support for simple prompts, full script uploads, reference images and even motion capture, inpainting and outpainting features.
AI as a Collaborative Partner
More recently, Lightricks has started to emphasize the idea that AI can be a kind of collaborative partner for human creators, taking care of all of the production work in video creation, so professionals can focus more on the story they’re trying to tell.
In an interview with iTechPost earlier this year, Farbman said the real magic occurs when you treat AI as a kind of co-creator, using it to build on your ideas. “It starts at the very beginning, at the spark of ideation,” he said. “You share a vision, a rough storyline, maybe some characters—and the AI brings it to life as a rich visual concept.”
The new capabilities in LTXV seem to reinforce that idea. “We’ve reached the point where AI video isn’t just prompted, but truly directed,” added Lightricks co-founder and CTO Yaron Inger in a statement. The new model, he said, essentially “turns AI video into a long-form storytelling platform, not just a visual trick.”
Nonetheless, it’s also clear that Lightricks hasn’t completely forgotten about its consumer roots, for the latest version of LTXV continues to be open-source, meaning it’s freely available for anyone to experiment with. Like previous editions of the model, it can be found on platforms such as Hugging Face and GitHub, and so long as you’re not using it to generate millions of dollars in revenue, it’s completely free to use and experiment with.
The model’s low resource requirements should also make it appeal to casual creators. Unlike other video models, such as OpenAI’s Sora, LTXV can run efficiently and generate high-quality, high-resolution outputs on a single H100 GPU, and it can even run on consumer-grade GPUs, the company claims. In contrast, most video generation models require as many as eight GPUs to produce quality video clips.
Also Read: AiThority Interview with Lokesh Jindal, Head of Products at Axtria
[To share your insights with us as part of editorial or sponsored content, please write to psen@itechseries.com]