Midjourney Launches Video Model V1 with Image-to-Video Animation

Midjourney’s Video Model V1 is now available to all users, enabling the conversion of images into animated video clips through a new “Animate” button. Each video job produces four 5-second clips, which can be extended in 4-second increments up to about 21 seconds. The platform supports both automatic and manual animation settings, including “low motion” for subtle changes and “high motion” for dynamic scenes. Users can also animate external images by uploading them and providing a motion prompt. This rollout is a clear pivot toward a larger vision: real-time, open-world AI simulation. Midjourney describes the video model as a foundational step, eventually to be joined by 3D and real-time components. The company’s goal is to integrate these elements into an interactive system where users can move through AI-generated environments in real-time. For now, V1 is web-only, with video generation costing around eight times more GPU time than image jobs—roughly the cost of one image per second of video. The new tool is part of Midjourney’s $10/month subscription plan, with premium tiers offering expanded access. Despite early pricing uncertainties, the company claims the new video jobs are over 25 times cheaper than similar offerings previously available on the market. This positions Midjourney as a serious contender in the AI video space, offering creators and developers a low-barrier entry into generative animation.