Midjourney has released version 1 of its AI video model, coming a week after the start-up was targeted in a copyright-infringement lawsuit by Disney and NBCUniversal.

At launch, Midjourney will charge about eight times more for a generative-AI video job than an image job; each job will produce four 5-second videos, the company said in a blog post. (According to one estimate, Midjourney’s pricing works out to 3-5 cents per image.) In the current model, once users have a video they like, they can extend it roughly 4 seconds at a time, four times total. The company claims the pricing is “over 25 times cheaper” compared with what has been available in the market before. Midjourney shared a sizzle reel of AI-generated video (watch below).

“Our goal is to give you something fun, easy, beautiful, and affordable so that everyone can explore. We think we’ve struck a solid balance,” says the June 18 blog post, which is signed “David” (presumably Midjourney founder and CEO David Holz).

The long-term vision, according to Midjourney, is “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 the blog post, David writes, “We ask that you please use these technologies responsibly. Properly utilized it’s not just fun, it can also be really useful, or even profound — to make old and new worlds suddenly alive.”

Midjourney has not issued a public statement about the Disney-NBCU lawsuit or responded to requests for comment. According to the studios, Midjourney is “the quintessential copyright free-rider and a bottomless pit of plagiarism” that has profited from their intellectual property. “Piracy is piracy, and whether an infringing image or video is made with AI or another technology does not make it any less infringing,” the Disney-NBCU lawsuit said, citing numerous examples of Midjourney’s system producing allegedly infringing images of Marvel superheroes, the yellow Minions from “Despicable Me,” and characters from Star Wars, “The Simpsons,” “Toy Story,” “Shrek” and more.

Midjourney’s blog post said that from a technical standpoint, the new video model “is a stepping stone, but for now, we had to figure out what to actually concretely give to you.” The company is calling the current video workflow “Image-to-Video,” meaning that you still make images in Midjourney but now you can press an “Animate” button to turn them into video clips. According to Midjourney, there’s an “automatic” animation setting as well as a “manual” animation setting that lets you “describe to the system how you want things to move and the scene to develop.”

The company also is allowing users to animate images “uploaded from outside of Midjourney.” To do this, users can drag an image to the prompt bar and mark it as a “start frame,” then type a motion prompt to describe how they want it to be animated.

Watch Midjourney’s AI video sizzle reel: