3 min readNew DelhiJun 20, 2025 09:06 AM IST
First published on: Jun 19, 2025 at 08:06 PM IST
AI research lab Midjourney has rolled out its first-ever, text-to-video generation model called V1.
The San Francisco-based firm on June 18, said that V1 can be used to convert images into a five-second AI-generated video clip. Users can either upload the images or use an AI-generated image by Midjourney itself. Then, the user can click “animate” to animate the image.
This creates four five-second AI-generated clips, which can be individually extendable to 20 seconds. It is unclear if these clips will also have sound. “The inevitable destination of this technology are models capable of real-time open-world simulations. What’s that? Basically; imagine an AI system that generates imagery in real-time,” Midjourney CEO David Holz said in a statement.
The animations generated through V1 can be either Automatic or Manual. In Automatic mode, the AI tool suggests a motion prompt to the user in order to make the image move while the Manual setting requires users to input prompts based on how they want the image to move and the scene to develop.
The user can also choose the camera style of the AI-generated video clip. The low-motion style is a stationary camera setting with slower camera movements while the high motion setting is a much more active camera setting, with the subject and the camera showing motion throughout the AI-generated animation.
Midjourney has made V1 accessible across all tiers, which means even free users of the platform can use the AI tool to create video clips. However, Midjourney said that creating a video will cost eight times more Graphics Processing Unit (GPU) time to the user as compared to generating still images. “This is amazing, surprising, and over 25 times cheaper than what the market has shipped before. It will only improve over time,” as per the AI firm.
Users can access V1 in ‘fast mode’ or ‘relax mode’. Fast mode entails using a set GPU time received every month. This is the mode available to all free and paid users, with one minute being used for image generation, and eight minutes used for video generation. Once this runs out, users cannot create any further AI-generated content on Midjourney.
Relax mode for videos is currently being tested for Midjourney Pro subscribers and above. It allows for unlimited GPU time. While image and video generation is unlimited, ‘relax mode’ takes longer (up to 10 minutes) as prompts wait in line to be completed.
(This article has been curated by Purv Ashar, who is an intern with The Indian Express)
A screengrab from Midjourney’s announcement video for V1 (Image: Midjourney) 
Share
