Midjourney Launches V1 AI Video Tool to Animate Still Images into Short Clips

Midjourney, a leading AI image-generation platform, has unveiled its first video tool—V1—enabling users to animate still images into short video clips. This marks a significant step for the company as it enters the fast-growing generative video space.

The new feature allows users to take an existing image—whether created within Midjourney or uploaded externally—and transform it into a video up to 21 seconds long. Users can initially create a five-second clip by clicking the “Animate” button, then extend the video by four seconds up to four times. The tool offers two animation styles: low-motion for subtle movement and high-motion for more dynamic effects, though the latter may produce occasional visual distortions.

Currently available through Midjourney’s web platform and Discord interface, the V1 feature is included in subscription plans beginning at $10 per month. Each second of video consumes roughly eight times the GPU time used for a single image—making the feature cost-effective compared to other video-generation tools on the market.

Midjourney’s founder, David Holz, described V1 as an early milestone toward more advanced goals like real-time simulations and immersive 3D experiences. He noted that the company’s long-term vision includes interactive and cinematic content generation.

However, the tool’s release comes amid legal challenges. Disney and Universal have filed lawsuits against Midjourney, accusing the platform of using copyrighted material to train its models. The addition of a video tool has intensified concerns about potential misuse of protected content.

Despite the controversy, V1 has received early praise for its ease of use and creative flexibility. Still, it lacks some advanced features—such as sound integration and detailed editing—that are offered by rivals like OpenAI’s Sora, Google’s Veo, and Adobe Firefly.