Midjourney Enters AI Video Race with 'V1', Turning Still Images into Animated Clips

SAN FRANCISCO – Midjourney, the independent research lab renowned for its powerful AI image generation tool, has officially stepped into the burgeoning field of AI video generation with the launch of 'V1'. Announced on Wednesday, June 18, 2025, the new model allows users to transform static images into short, five-second animated videos, marking a significant expansion of the platform's creative capabilities. The V1 model is designed with accessibility in mind, integrating seamlessly into the existing Midjourney workflow primarily hosted on Discord. Users can take any image they've generated with Midjourney or upload their own, and with a simple 'Animate' command, V1 will produce four distinct video clips based on the source image. This move places Midjourney in direct competition with other major players in the AI video space, including OpenAI's Sora, Runway, and Google's Veo. While initial examples showcase a more ethereal and dreamlike quality, reminiscent of Midjourney's signature artistic style, the company has incorporated features for user control. Users can opt for an 'auto' setting for random motion or manually adjust the level of camera and subject movement, selecting between 'low motion' and 'high motion' to influence the final output. While the base video length is five seconds, a key feature is the ability to extend these clips by up to four seconds at a time, allowing for a maximum video length of 21 seconds. This extensibility offers a degree of narrative potential not always present in short-form AI video generation. The launch, however, comes with a new pricing structure. Video generation is reported to be eight times more costly in terms of platform resources than image generation. This premium cost underscores the immense computational power required to render video compared to still images. The V1 feature is currently available to users with premium subscriptions on the Midjourney web platform, with plans for wider accessibility in the future. Industry analysts view this as a crucial step for Midjourney to maintain its position as a leader in the generative AI space. As text-to-video technology becomes more sophisticated and accessible, offering a native video solution was seen as an essential evolution for the platform. Early user reactions have been largely positive, with creators experimenting with animating their favorite AI-generated artworks. The community is already exploring novel uses, from creating dynamic avatars and animated logos to short, artistic visual poems. Midjourney has indicated that V1 is just the beginning of its foray into moving pictures. The company has publicly stated its long-term plans include developing models for 3D rendering and real-time generative applications, signaling a broader ambition to build a comprehensive suite of tools for next-generation digital creativity. The release of V1 will undoubtedly accelerate the pace of innovation in AI video, as a platform with millions of dedicated users begins to explore and push the boundaries of what's possible with animated AI content.