HomeArtificial Intelligence“We don’t need Sora anymore”: Luma’s recent AI video generator Dream Machine...

“We don’t need Sora anymore”: Luma’s recent AI video generator Dream Machine was overloaded with traffic after its debut

The fast-moving AI video generation market has modified again: Luma AI, a startup backed by famed Silicon Valley enterprise firm Andreessen Horowitz, today announced the free public beta of its recent AI video generation model. Dream machineand it has already encountered a rush of users.

Although the model guarantees to generate as much as 120 frames in 120 seconds (2 minutes or one frame per second), in point of fact many users need to wait for hours in a digital queue on the Luma Dream Machine website for his or her video to be processed, because of the big volume of information involved, in keeping with the corporate.

wrote Barkley Dai, Luma’s Head of Product and Growth, in a Message on the corporate's Discord channel today.

A number of hours later, Dai provided the next update:

“..

The high-quality AI video generator comes from little-known startup Luma AI, which VentureBeat previously covered when it released its text-to-3D asset generator model Genie 1.0 in November 2023. Luma AI has raised greater than $70 million, including $43 million in its Series B starting in January 2024. in keeping with TechCrunch.

From a PR perspective, the corporate has previously staffed Dream Machine with outstanding AI video producers and filmmakers. They had the chance to check the software's ability to generate videos from text prompts and still images before today's public beta launch, and posted their work throughout the day.

Others who are only getting their hands on it also find it extremely impressive, inviting comparisons to OpenAI's Sora, while some say it’s already superior.

In VentureBeat's limited testing of Luma's Dream Machine web app, the accuracy of the text-to-video feature was spotty when displaying our query. However, the video was generated in several minutes and contained extremely smooth, jerk-free motion and high-resolution, detailed assets.

Clearly, the race to create compelling AI video models is entering a brand new phase, and OpenAI's Sora, still only available to a small group of hand-picked users, now faces some seriously tough competition – not to say other AI video model providers Runway, Pika, and recent Chinese competitor Kling.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Must Read