Luma AI, a startup supported by Andreessen Horowitz, has launched the free public beta of its AI video generation model, Dream Machine, attracting a significant user turnout that resulted in long wait times. The model, designed to produce up to 120 frames in 120 seconds, faced delays due to an unexpectedly high volume of traffic, with users experiencing hours-long waits in a digital queue on the company’s website.
Barkley Dai, the product and growth lead at Luma, addressed the issue on the company’s Discord channel: “Hey everyone, thanks so much for all the enthusiasm and support! We are 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!” Later, Dai announced, “Our team added additional capacity and as a result, the queue is now gradually shorter! In the near term, we estimate that it may still take a few hours to fully process the current backlog of pending generations. Under normal conditions – it will only take 2-3 minutes to turn your prompt into a video & we appreciate your patience as we deal with the influx of people interested in trying this revolutionary tool. Generation speed will continue to improve… They will generate as soon as possible and we appreciate everyone’s patience and support today and encourage you to continue to revisit throughout the rest of the week and beyond as we improve Dream Machine.”
The Dream Machine is the latest release from Luma AI, a relatively lesser-known firm that also launched its text-to-3D asset generator, Genie 1.0, in November 2023. Luma AI has raised over $70 million, including $43 million in its Series B round as of January 2024.
Prior to the public beta release, the company strategically provided early access to Dream Machine to notable AI video creators and filmmakers, allowing them to showcase their creations made from text prompts and still images. Their works were shared throughout the day of the launch.
Feedback from users who have tested the Dream Machine has been overwhelmingly positive, with some comparing it favorably to OpenAI’s Sora and others suggesting it may already surpass it. The Dream Machine’s text-to-video feature does still show some sporadic accuracy in matching the prompts, but produces videos with smooth motion and high-resolution, detailed assets.
As AI video technology advances, Luma AI’s Dream Machine is positioning itself as a formidable competitor in the field, challenging established models like OpenAI’s Sora, as well as other providers such as Runway, Pika, and another brand new competitor, Kling.
