Luma AI releases Ray2 video generator with better physics

Luma AI made waves upon its launch A dream machine next-generation AI video creation platform last summer.

In fact, although that was only seven months ago, the AI ​​video space has progressed rapidly with the release of many new AI video creation models from competing startups in the US and China, including Runway, A sword, Pic 2.0, Sora at OpenAI, I see 2 at Google, Hailuo at MiniMax and open source alternatives like Hot shot and Mochi Genmo 1to name a few. Even Luma itself recently updated Dream Machine platform to include new still image generation and brainstorming boards, as well as a discontinued iOS app.

But the updates continue: Today, the start-up based in San Francisco has been published Ray2, its latest AI video generation module, available now through its Dream Machine website and mobile apps for paying subscribers (for starters).

The model offers “fast, natural and sensible movement and physics,” according to the co-founder and CEO Amit Jain says on his account Xand was trained with 10 times more computing power than the original Luma AI video model, Ray1.

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

Luma's Dream Machine web platform offers a free tier with 720 pixel generations capped at a variable number per month: Paid plans start at $6.99 per month: From “Lite,” which offers 1080p visuals, to Plus ($20.99/ month), to Unlimited ($66.49/month) and Enterprise ($1,672.92/year).

Skip ahead in video gen

Currently, Ray2 is limited to tex-to-video, allowing users to type descriptions that are converted into 5 or 10 second video clips.

The model can generate new videos in a couple of seconds, but currently it can take minutes at a time due to the pressure of demand from new users.

Examples shared by Luma and early testers in its Creators program showcase the model's versatility, including a man running through an Antarctic snowstorm surrounded by explosions, and a ballerina playing on an ice floe in the Arctic.

Impressively, every movement in the example videos appears alive and fluid – and often, with subjects moving much faster and more naturally than videos from competing AI generators, which often seem to ' generated in slow motion.

The model can even create realistic versions of surreal ideas such as a giraffe surfas user X @JeffSynthesized presented. “Ray 2 is the real deal,” he said write on X.

Other AI video creators who have tried the new model seem to largely agree, with Jerrod Lew posts on X: “Improved cinematography, lighting and astronomy have arrived and it's brilliant.”

“…it's so good!” AI video artist Heather Cooper shock in.

My own tests were a mixed bag, with more complex suggestions creating unnatural and glitchy results. But when he brought out clips that looked like more of what I had in mind in my suggestions – like fences crossing swords aboard a space station orbiting Jupiter – no doubt it was impressive.

Jain said Luma will also add image-to-video, video-to-video and editing capabilities to Ray2 in the future, further expanding the device's creative potential.

To celebrate the launch of Ray2, Luma Labs is hosting the Ray2 Awards, giving creators the chance to win up to $7,000 in prizes. These include:

1. Prize on a large scale: The creator whose content Ray2 collects the most views on one platform in the first week of launch $ 5,000. Applications are due by January 22, 2025.
2. Raffle for $3,000: Creators can enter by sharing Ray2 content on social media and participating in the Luma AI launch video. The deadline for participation is also January 22.

The winners of both awards will be announced on January 27. Submissions can be uploaded via forms provided by Luma Labs, and creators are encouraged to use the hashtags #Ray2 and #DreamMachine when sharing their work.

In addition, Luma Labs has launched an affiliate program, which allows partners to earn commissions by promoting their tools.