Midjourney unveils first-ever AI video model ‘V1’ amid rising competition

In a remarkable development, the renowned artificial intelligence (AI) image generation startup Midjourney has launched its first-ever video generation model.

Dubbed  “V1,” the new tool allows users to input a single image either user-uploaded or generated through Midjourney’s other models, and transforms it into four five-second video clips.

Like its image models, V1 is currently accessible through Midjourney’s Discord server.

This launch comes just a week after Midjourney was sued by two of Hollywood’s renowned film studios, “Disney” and “Universal.”

The lawsuit has alleged that images created by Midjourney’s AI image models depict the studio’s copyrighted characters, such as Homer Simpson and Darth Vader.

The launch marks a significant expansion for the company as it steps into the competitive field of AI video generation.

It now joins the ranks of major players like OpenAI’s Sora, Runway’s Gen-4, Adobe’s Firefly, and Google’s Veo 3.

While many rivals focus on creating content for marketing and commercial purposes, Midjourney aims to cater more to the creative community and artists.

Midjourney CEO David Holz described the release as a step toward more ambitious goals, including the creation of AI models capable of powering real-time, open-world simulations.