Midjourney, best known for its AI Image Generator, has announced its first video generation model called the V1 Video.
Users can generate 5-second clips using written prompts and images. It is an AI image of Midjourney image generator, or you can upload one of your own. Videos can be expanded for up to 21 seconds and up to 4 times in 4 seconds increments. Depending on whether both the subject and camera move, or just the subject, the animation can be adjusted with either low animal or high movement.
The new tool is accessible through the Midjourney website and Discord Server and is part of the subscription plan starting at $10 per month. That plan will provide 3.3 hours of “fast” GPU time, roughly equivalent to the 200 generation. However, video jobs cost about 8 times more than a single image generation, or “one image equivalent to one second cost per second of video”, which costs quite a lot of resource-intensive costs.
Introducing the V1 video model. It's fun, easy and beautiful. Available for $10/month. This is the first video model for Everyone, and is currently available. pic.twitter.com/ibm0kan8uy
– Midjourney (@midjourney) June 18, 2025
In automatic mode, the default prompts are used to generate basic movements, but the manual option allows the user to explain the motion in more detail. Midjourney founder David Holz describes the release as a “footstone” for more advanced models such as “real-time open world simulation.”
“This means creating images in Midjourney as usual, but now you can press 'animation' to move,” Holz said in a blog post. “It's not only good use, it's fun, but it's also really convenient or even deeper to bring the old and new worlds to life all of a sudden.”
Rollouts come at a sensitive time for the company. Last week, Disney and NBCuniversal filed a lawsuit against Midi Johnny citing concerns about the potential misuse of copyrighted content. The company claims that the platform “acts as a virtual vending machine and generates endless, unauthorized copies of Disney and Universal copyrighted works.” The lawsuit also raises alarms about how Midi Joanie models train, claiming they are infringing.
Despite running around other companies like Openai, Google and Adobe in the text-to-video field, Midjourney's move to animation shows that it is intended to stay competitive. Tools like Google's VEO, Openai's SORA, Adobe's Firefly Video and more have already implemented more sophisticated and quick video capabilities.
Holz acknowledges the challenges of scaling video tools, saying, “The actual costs of creating these models and the prices we charge are difficult to predict.” He added that pricing and availability could change over the coming weeks as usage patterns emerge.
Midjourney urged users to “use these technologies responsibly.”
