Skip to main content
  1. Home
  2. Computing
  3. News

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

By
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.

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.

Recommended Videos

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!”

Related

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.

Editors’ Recommendations

Topics
Andrew Tarantola
Andrew Tarantola
Computing Writer
Andrew Tarantola is a journalist with more than a decade reporting on emerging technologies ranging from robotics and machine…
Is AI already plateauing? New reporting suggests GPT-5 may be in trouble
A person sits in front of a laptop. On the laptop screen is the home page for OpenAI's ChatGPT artificial intelligence chatbot.

OpenAI's next-generation Orion model of ChatGPT, which is both rumored and denied to be arriving by the end of the year, may not be all it's been hyped to be once it arrives, according to a new report from The Information.

Citing anonymous OpenAI employees, the report claims the Orion model has shown a "far smaller" improvement over its GPT-4 predecessor than GPT-4 showed over GPT-3. Those sources also note that Orion "isn’t reliably better than its predecessor [GPT-4] in handling certain tasks," specifically coding applications, though the new model is notably stronger at general language capabilities, such as summarizing documents or generating emails.

Read more
OpenAI could release its next-generation model by December
ChatGPT giving a response about its knowledge cutoff.

OpenAI plans to release its next-generation frontier model, code-named Orion and rumored to actually be GPT-5, by December, according to an exclusive report from The Verge. However, OpenAI boss Sam Altman is already pushing back.

According to "sources familiar with the plan," Orion will not initially be released to the general public, as the previous GPT-4 variants were. Instead, the company intends to hand the new model over to select businesses and partners, who will then use it as a platform to build their own products and services. This is the same strategy that Nvidia is pursuing with its NVLM 1.0 family of large language models (LLMs).

Read more
Radiohead’s Thom Yorke among thousands of artists who issue AI protest
Thom Yorke on stage.

Leading actors, authors, musicians, and novelists are among 11,500 artists to have put their name to a statement calling for a halt to the unlicensed use of creative works to train generative AI tools like OpenAI’s ChatGPT, describing it as a “threat” to the livelihoods of creators.

The open letter, comprising just 29 words, says: “The unlicensed use of creative works for training generative AI is a major, unjust threat to the livelihoods of the people behind those works, and must not be permitted.”

Read more