Midjourney released the first version of the video generation model to the public. For now, the tool can generate short videos based on images uploaded or created on the platform, but Midjourney plans to roll out more features in the future.
After creating an image using Midjourney, the service will display a new “Animation” button that allows users to create a 5-second clip based on a text prompt. You will also be given the option to add the image you uploaded to the platform as a “start frame” for your video. By default, the tool generates a general prompt that says “just move things”, but the “Manual” button allows you to explain how the user wants to see the motion.
Users can expand the animation up to four times, creating a total of 21 seconds of video. There are also high and low motion settings that control whether both the subject and camera move, or just the subject.
Midjourney's AI video generator is currently only available on the web and on Startup's Discord servers. A subscription to the service is required. This subscription starts at $10 per month for 3.3 hours of “fast” GPU times (approximately 200 image generation). The startup says it charges “about 8 times more video jobs than video jobs” and sums around “one image equivalent of the cost per second of video.”
Midjourney is currently the subject of lawsuits from Disney and Universal, which cited the prospect of launching a video generator as a special concern. Midjourney claims that it “provides virtual vending machines and produces endless, unauthorized copies of Disney and Universal copyrighted works.” The ongoing video generation model was first announced in January, with Disney and Universal claiming that its training process “is likely that the Mid Journey already infringes the plaintiff's copyrighted work.”
In a post announcing the generator, Midjourney founder David Holz says that this first version is nothing more than a “stepping stone” as it works to create “models that allow for real-time open-world simulations.” Google, Openai and Meta have also launched AI video generators. All of these can be generated by a text prompt.
