It is uncommon to see an AI video mannequin that is not the technological equal of a closed black field, and it is even rarer to see a video mannequin that is optimized sufficient to run regionally in your units fairly than counting on cloud-based providers. Lightricks-2, a brand new AI mannequin video inbuilt partnership with Nvidia, can do each.
Lightricks debuted the mannequin with Nvidia at CES 2026, one of many largest tech commerce exhibits. Nvidia additionally confirmed off plenty of AI-powered and next-generation software updates for gamers, together with an agentic assistant, an academic advisor and an AI upscaler for smoother, extra outlined graphics.
Watch this: Each Announcement from the Nvidia Reside CES 2026 Stream
Lightricks’ new mannequin will be capable to create AI clips which can be as much as 20 seconds lengthy, 50 frames per second — that is on the longer finish of the spectrum of the trade’s AI video capabilities. The mannequin will even embrace native audio. The power to generate in 4K will probably be essential for creators who need to use the brand new mannequin for professional-grade initiatives. But it surely’s the on-device capabilities that basically set the brand new mannequin other than opponents like Google’s Veo 3 and OpenAI’s Sora.
The mannequin was constructed with skilled creators in thoughts, whether or not that is particular person filmmakers or massive studios. The concentrate on the standard of the clip, together with its on-device optimizations, goals to make it one of many extra interesting and safe choices for AI-inclined creators.Â
For extra on {hardware} from CES, try HP’s new IT-friendly business laptops and AMD’s speedy mobile processors.
What’s totally different about Lightricks’ new mannequin
When AI corporations speak about “open” fashions, they’re usually referring to open-weight AI models. These fashions aren’t actually open-source, which requires each a part of the method to be disclosed. However they do give builders insights into how the mannequin was constructed. The weights are like substances in a cake; open-weights fashions let you know all of the substances that went into the batter, however you do not know the precise measurements of every. Lightricks’ mannequin is open-weight and obtainable now on HuggingFace and ComfyUI.
That is an instance of the extent of element in LTX-2 AI movies.
Lightricks’ new video mannequin can be capable of run locally on your devices. This isn’t usually the case for AI video. Producing even brief AI video clips is a really compute-intensive course of, which is why video fashions use more energy than different AI instruments. To get the perfect outcomes with most AI video mills, you are going to need information middle computer systems utilized by Google or OpenAI to do the heavy lifting and generate your movies within the cloud fairly than in your laptop computer or cellphone. With Nvidia’s RTX chips, you may get these high-quality outcomes with out outsourcing the workload to a cloud service.
There are quite a lot of advantages to operating AI fashions regionally. You are in command of your information; you do not have to share it with massive tech corporations that will use it to enhance their very own AI fashions. That is an especially vital issue for large leisure studios which can be diving into generative AI however need to protect their intellectual property rights. Operating AI fashions in your machine, with the correct tools, can even offer you outcomes sooner. The common AI video immediate takes 1-2 minutes to generate, so decreasing that might assist save money and time, that are two of the strongest arguments for creators integrating AI into their work.Â
For extra, try the AI note-taking ring expanding the AI wearable industry and the new Gemini features coming to Google TV devices.
