Skip to main content

This new text-to-video AI looks incredible, and you can try it for free

An AI-generated image of a woman wearing a yellow dress seated in front of a similarly colored floral background.
Luma AI

Expectant AI enthusiasts flooded the Luma AI website on Wednesday, resulting in multi-hour waits to access the company’s new free-to-use, high-definition AI video generator, Dream Machine, Venture Beat reports.

Recommended Videos

What’s all the excitement for? Well, the Andreessen Horowitz-backed startup’s model promises video generation of up to 120 frames per second for as long as 120 seconds. And based on some of the examples being shared online so far, it’s pretty impressive.

Welcome @LumaLabsAI to the AI Video wars It makes so much sense that your technology – which makes 3D models- lends itself to high quality video generation. I've remade my Brothers Grimm fairy tales video with your new tool. More examples below 👇

So it's Dream Machine. I'm a… pic.twitter.com/KXT9FvurWV

— Max Einhorn (@MaxEinhorn) June 12, 2024

“Hey everyone, thanks so much for all the enthusiasm and support!” Barkley Dai, Luma’s head of product and growth, wrote in a message on the firm’s Discord channel Wednesday. “We are current[ly] facing high demands and working on increasing our capacity! All the generations won’t be lost but it will just be staying in the queue. Will update the status here once we have additional capacity!”

As of Thursday morning, the queue for service with Dream Machine was a little over one minute, a significant improvement over the previous afternoon’s wait times. Part of Dream Machine’s immediate success can be attributed to Luma’s previous efforts to reach out to prominent AI video creators ahead of the public beta release, giving them a sneak preview of the model’s capabilities and allowing them to share their generated creations throughout the day.

Luma AI dropped their Sora competitor & it's insane

The best part? They are actually letting people use it

10 awesome examples with prompts: pic.twitter.com/vcDsAQjjD1

— Allen T. (@Mr_AllenT) June 12, 2024

Initial feedback from the creators was generally positive, with users able to generate five-second-long videos in a couple of minutes based solely from text-based prompts. A number of users even made direct comparisons to OpenAI’s Sora, widely considered to be the current state of the art in AI video generation.

We don't need Sora anymore :) #LumaDreamMachine

I'll be posting more creations soon, this is AMAZING! pic.twitter.com/ldBoPIbeF2

— Kiri (@Kyrannio) June 12, 2024

Dream Machine’s free tier allows users to generate up to 30 video clips per month, though higher paid tiers will allow for up to 2,000 video generations per month at a cost of $499. Luma AI’s offering is merely the latest entry into an increasingly crowded and hotly contested AI space.

Other free services like Google’s Lumiere, Runway, Pika, and Kling, from China’s Kuaishou company, are all similarly looking to chip away at Sora’s lead. You can try Dream Machine for yourself at the Luma AI website.

Andrew Tarantola
Former Digital Trends Contributor
Andrew Tarantola is a journalist with more than a decade reporting on emerging technologies ranging from robotics and machine…
OpenAI releases a new AI model, but it’s eye-wateringly expensive
OpenAI's new typeface OpenAI Sans

OpenAI has released its latest model, o1-pro, an updated version of its reasoning model o1 -- but it's not going to come cheap.

"It uses more compute than o1 to provide consistently better responses," OpenAI said in its announcement. The company went on to say it offered new features including: "Supports vision, function calling, Structured Outputs, and works with the Responses and Batch APIs. "

Read more
Why OpenAI’s copyright plan will impact you more than you think
Depiction of OpenAI Sora video generator on a phone.

OpenAI is inconsistent in a lot of things -- is it a non-profit or a for-profit? Is Sam Altman fit to be CEO or not? But one thing the company has always been consistent about is its belief that it requires access to copyrighted material for AI training. Now, despite the many voices that disagree, OpenAI wants the U.S. government to approve such unrestricted access by ruling it as "fair use."

The company argues that the U.S. will fall behind China in the AI race if companies don't have the freedom to train their models on copyrighted material -- claiming that "overly burdensome state laws" will slow the process and affect results.

Read more
I was struck by OpenAI’s new model — for all the wrong reasons
Announcement artwork for GPT 4.5 AI model

Sam Altman has shared a snippet from a new OpenAI model trained for creative writing. He says it's the first time he's been "struck" by something AI has written but the comments section is a total mess of extreme agreement and disagreement.

https://x.com/sama/status/1899535387435086115

Read more