In a groundbreaking move, Midjourney, a leading name in AI image generation, has launched its first-ever AI video generation model, dubbed V1. Announced on June 18, 2025, this innovative tool marks the company's exciting transition from static images to dynamic multimedia content, opening new creative possibilities for users worldwide.
The V1 model is an image-to-video system that allows users to transform a single static image into short animated clips. Specifically, it generates four 5-second videos per job, with the option to extend clips up to 20 seconds total. Users can also adjust settings for high or low motion to customize the level of action in their videos.
Accessible exclusively through Midjourney’s web platform and Discord, V1 is available to all subscription tiers at no additional cost for basic access, though video generation is priced at 8x the cost of image generation. Midjourney claims this pricing is still 25x cheaper than competing AI video tools, making it an attractive option for creators on a budget.
Key features of V1 include support for external image uploads, a cinematic and dreamlike style, and rapid generation times of just 3-5 seconds for initial clips. This positions Midjourney as a serious contender in the AI video space, competing with established players like Runway and Adobe.
The launch of V1 signals Midjourney’s ambition to redefine creative AI tools, catering to artists, marketers, and content creators seeking innovative ways to animate their visions. Early feedback from select users highlights the model’s ease of use and stunning visual output, though some note the current limitation on video length as an area for future improvement.
As Midjourney continues to refine its technology, the introduction of V1 is a significant step toward a future where AI seamlessly blends static and moving imagery. This release not only expands the company’s offerings but also sets the stage for further advancements in multimedia AI applications.
Andrew Lee
