Midjourney has just taken a major step into AI video generation. If you’re already familiar with its AI-powered image generator, you’ll be excited to hear that it allows you to animate your creations into short video clips. This new feature is part of Midjourney’s growing ambition to expand beyond still images and into dynamic visual storytelling.
A simple way to bring your images to life
When you generate an image using Midjourney, you’ll now see a new “animate” button. You can turn that image into a five-second video with a single click. The animation is based on a text prompt, allowing you to control how the image moves. If you prefer not to write a prompt, the tool automatically creates a default version that adds motion. You can also click a “manual” option to give specific instructions about the animation’s style and direction.
Introducing our V1 Video Model. It’s fun, easy, and beautiful. Available at 10$/month, it’s the first video model for *everyone* and it’s available now. pic.twitter.com/iBm0KAN8uy
— Midjourney (@midjourney) June 18, 2025
That’s not all—you can upload your image and use it as the starting point for your animation. This means you’re not limited to what Midjourney creates. Whether you’ve drawn something or a photo you love, the platform will treat it as the first frame and generate a video from there.
Want your clip to be longer? You can extend the animation by four seconds at a time, up to four times. That gives you a total possible length of 21 seconds. There are two settings for movement: low motion and high motion. The low motion option will move only the subject in the video, while the high motion option also shifts the camera’s viewpoint for a more dramatic effect.
Available now, but with limitations
Midjourney’s AI video generator is now only accessible via its web platform and Discord server. You’ll need a paid subscription to use it, with prices starting at US$10 per month. This entry-level plan includes 3.3 hours of “fast” GPU time, which roughly equals 200 image generations.
However, video generation uses significantly more processing power. According to Midjourney, a single second of video will cost about the same as generating one image. That means a 5-second clip could cost up to five times as much, depending on your plan and usage.
This release is just the beginning. Midjourney’s founder, David Holz, described this early version as a “stepping stone” toward more advanced tools. The company aims to build models that could simulate real-time, open-world environments.
Facing legal challenges as it moves forward
Despite the excitement around the tool, Midjourney’s video model is under legal scrutiny. Major film studios Disney and Universal have already filed a lawsuit against the company. Their complaint mentions concerns over Midjourney’s move into video, accusing it of being a “virtual vending machine” that creates unlimited unauthorised copies of their copyrighted work.
The studios believe Midjourney’s AI was trained using copyrighted material without permission. They argue that the model infringes on intellectual property even in this early form. The lawsuit began after Midjourney first teased its video capabilities in January.
Midjourney is not alone in the race to perfect AI-generated video. Competitors like Google, OpenAI, and Meta have also launched their versions of text-to-video tools. Still, this release puts Midjourney squarely in the spotlight as it attempts to shape the future of how we create and experience visual content.
