Luma AI created an AI video model that 'reasons' - what it does differently
Briefly

Luma AI created an AI video model that 'reasons' - what it does differently
"Just a few years ago, AI-generated video clips were a laughing stock on the internet -- anyone remember the nightmarish video of AI-generated Will Smith wolfing down spaghetti ? The technology has come a long way since then: Today, tech startups are competing to deliver generative AI tools which, at least in their vision of the future, aim to rival the quality of Hollywood production studios -- at a tiny fraction of the cost."
"You've heard of so-called reasoning models like OpenAI's o3, which are thought to consider a query, especially complex ones, for more time than standard generative AI models in order to return a more helpful and thorough answer. But thus far, those models haven't had video-generating capabilities. Ray3, according to Luma AI, stands apart from competing tools from companies like Google, Runway, Meta, and OpenAI primarily due to its ability to "reason" while generating video clips."
AI-generated video quality has improved from early low-quality clips to tools aspiring to match Hollywood production at much lower cost. Startups are developing generative video tools aimed at creative industries and automated creative partnerships. Luma AI announced Ray3 and Luma Dream Machine to generate videos from photos. The Ray3 model is available now and is accessible to paying Adobe Firefly and Creative Cloud Pro customers for unlimited videos until Oct. 1. Ray3 is presented as a reasoning-capable video model, claiming multimodal reasoning while generating clips, distinguishing it from other companies' video tools.
Read at ZDNET
Unable to calculate read time
[
|
]