Luma AI Announces Ray2 AI Video Model Pre-trained with ‘10x Compute’

Luma Labs has introduced a new video generative model called Ray2. It claims to create realistic videos with natural and coherent motion. Ray2 is currently available on the Dream Machine platform for paid subscribers.

“We are starting with text-to-video. Image-to-video, video-to-video, and editing capabilities will soon follow,” said the company in a post on X. It can generate videos with a duration of five or ten seconds in multiple aspect ratios. The paid plans for Dream Machine start at £6.99 a month and enable users to create 1080p videos. 

“Today, we are introducing Ray2! Scaling pretraining by 10x (in comparison to Ray1) on a novel efficient architecture, we are able to unlock the next frontier in video generation—fast natural coherent motion and physics,” said Amit Jain, co-founder of Luma Labs, in a post on X.

“This skyrockets the success rate of usable, production-ready generations and makes video storytelling accessible to many more people,” he added. 

Jain also revealed that the company is considering releasing an API for it soon and that it is ‘essential to our goals’. 

The company also released a long list of examples of videos generated across themes like natural motion, physics and simulation, photorealism, cinematic scenes, people and expressions.

Ray 2 produces AI influencers on demand — complete with wide angle vlogging and rolling shutter 🫣 pic.twitter.com/uUvgaX944u

— Bilawal Sidhu (@bilawalsidhu) January 15, 2025

That said, users did run into a few issues accessing the model on launch day. One user on X complained that the servers were overwhelmed and that they had been waiting for 30 minutes for the result. 

Meanwhile, Jain noted that it was the ‘launch day rush’ and expected that things would stabilise soon. 

Users quickly tested the model. MattVidPro, an AI-focused tech YouTuber, conducted a poll on X, asking testers which model is more impressive: Ray 2, Google’s Veo 2, or Vidu 2 from Vidu AI. The results revealed that over 80% picked Google’s Veo 2 model. 

A user on X, Ben Nash, expressed that Veo is significantly ahead of its competitors and believes it is of superior quality compared to Sora, even though Sora offers a greater array of features. However, unlike OpenAI's Sora and Ray 2, Google’s Veo 2 is not yet available for public use.

Google’s internal testing indicates that Veo outperforms competitors (such as China’s Kling, Meta’s Moviegen, and OpenAI’s Sora) both in terms of quality and prompt adherence.