3 minute read

Midjourney has officially stepped into the world of video. In a major update, they’ve released Version 1 of their long-anticipated Image-to-Video feature, allowing users to animate their AI-generated images—and even upload their own—to create short, dynamic videos.

What Is Image-to-Video?

Dragon art created from Midjourney AI
PROMPT: A majestic dragon sitting on top of a mountain top breathing fire into the sky. The look of the scene should resemble Harry Potter colors and design. –v 5.2

The new tool allows users to take any image generated in Midjourney and press an “Animate” button to turn it into a short video. You can choose between two animation styles:

  • Automatic Mode: Midjourney generates a motion prompt for you. Think of it as a “just make it move” button.
  • Manual Mode: You write your own motion prompt to guide the animation exactly how you want.

You can also choose between low motion and high motion settings:

  • Low motion works well for ambient scenes with minimal camera movement.
  • High motion is for more dramatic scenes with moving subjects and camera pans, though it can introduce more visual quirks.

Each video clip is around 5 seconds long, and you can extend a video up to four times (up to 20 seconds total).

You Can Animate Your Own Images Too

dragon animated with midjourney image to video feature
Watch full resolution video here

In addition to Midjourney-created images, users can upload their own image, drag it into the prompt bar, mark it as a “start frame,” and describe how they want it to move using a motion prompt. It’s a major step forward for creators who want more control and flexibility.

Cost and Availability

For now, the feature is web-only and costs about 8x the price of a single image job. But considering you get four 5-second video clips per job, it breaks down to one image’s worth of cost per second of video—which is significantly cheaper than most competing video generation tools on the market today.

For Pro users and above, a Video Relax Mode is also being tested, offering lower-priority render times for a lower cost.

The Bigger Picture

This release is part of Midjourney’s larger vision: building toward real-time, open-world AI simulations. To get there, they need to develop the building blocks—image models, video models, 3D models, and real-time rendering. The Image-to-Video release is just one step in that process, but a big one.

This launch represents more than just a fun new toy. It’s a serious shift toward the future of interactive, generative media. Whether you’re an artist, creator, marketer, or just curious, now’s a great time to dive in and see what’s possible.

Midjourney’s new tool is fast, affordable (relatively speaking), and full of potential. And if this is just the beginning, it’s safe to say there’s much more on the horizon.