Lightricks LTX Studio Is a Text-to-Video Filmmaking Platform

Lightricks, the company behind apps including Facetune, Photoleap and Videoleap, has come up with a text-to-video tool called LTX Studio that it is being positioned as a turnkey AI tool for filmmakers and other creators. “From concept to creation,” the new app aims to enable “the transformation of a single idea into a cohesive, AI-generated video.” Currently waitlisted, Lightricks says it will make the web-based tool available to the public for free, at least initially, beginning in April, allowing users to “direct each scene down to specific camera angles with specialized AI.”

The interface is designed for simplicity: “Creators can first type an idea they have and LTX Studio will create a script and a storyboard for them along with characters through a prompt,” writes TechCrunch, explaining that “the storyboard shows different scenes divided into many shots.” Each shot typically runs a few seconds.

Scenes can be changed using prompts to change styles from, say, cinematic to anime. Other settings, such as weather and location, can also be modified. Camera angles, special effects, motion scale and sound can all be adjusted using the shot editor.

“Users can also add, remove, or modify characters for the whole concept through a separate characters tab,” reports TechCrunch, adding images “with a visible face” can also be imported to create characters that will appear in the storyline. Lightricks emphasized “character consistency” from concept to completion as a key feature creators were requesting.

The Israeli startup “expects the first version of the software to be used more for smaller efforts or commercial storyboarding and pre-production than for creating finished movies,” Axios reports.

SiliconANGLE calls text-to-video “the cutting edge of generative AI technology,” where Lightricks faces tough competition in the space. OpenAI recently unveiled a new model called Sora that generates up to a minute of contiguous video that can be photorealistic, maintaining fidelity to user prompts. Startups Runway and Pika Labs are also playing in the text-to-video space.

Stability AI has Stable Video Diffusion, while Google has Lumiere. Meta Platforms was an early entry in the field, launching Make-A-Video in 2022, and recently teased a more sophisticated model called Emu.

But LTX Studio aims to “take things up a notch,” SiliconANGLE writes, specifying its aim to “make videos that look and feel realistic,” with an interface that’s easier to use.

No Comments Yet

You can be the first to comment!

Leave a comment

You must be logged in to post a comment.