English
Gamereactor
lifestyle

Midjourney expands into real-time generated AI videos as part of latest update

It's the first step towards real-time open-world simulations.

Subscribe to our newsletter here!

* Required field
HQ

Artificial intelligence company Midjourney has recently unveiled its next major step forward. Following years of offering and focussing on still images, Midjourney is now looking to expand into the world of video generation, specifically real-time generation.

This is now available as part of Version 1 of the Video Model, which is described as "something fun, easy, beautiful, and affordable so that everyone can explore." At the moment, the system is meant to turn images into video by using an animate motion prompt mechanic. Essentially, it brings life and movement to a still image, which can be tweaked depending on the level of motion that should be expected from the source image in question.

Compared to rival AI video software, it might seem like Midjourney is a bit behind, but it notes that this is just a stepping stone towards a much greater goal. The long-term intention is to be able to offer real-time open-world simulations, and getting there means also being able to move through 3D models of generated video, and then also generating everything very fast. These latter points are the next steps towards making Midjourney's aim a reality. In Midjourney's own words:

"What you might not know, is that we believe the inevitable destination of this technology are models capable of real-time open-world simulations.

This is an ad:

"What's that? Basically; imagine an AI system that generates imagery in real-time. You can command it to move around in 3D space, the environments and characters also move, and you can interact with everything.

"In order to do this, we need building blocks. We need visuals (our first image models). We need to make those images move (video models). We need to be able to move ourselves through space (3D models) and we need to be able to do this all fast (real-time models).

"The next year involves building these pieces individually, releasing them, and then slowly, putting it all together into a single unified system. It might be expensive at first, but sooner than you'd think, it's something everyone will be able to use."

The catch with this video software is that it's much more expensive to use. Midjourney is charging 8x what it charges for an image job, which it describes is still "over 25 times cheaper than what the market has shipped before."

This is an ad:
Midjourney expands into real-time generated AI videos as part of latest update


Loading next content