You can now create AI videos with Midjourney

AI Video & Visuals


The PCMAG Editor selects and reviews products independently. If you make a purchase through affiliate links, you may earn a commission that will help you support your testing.

AI image generator Midjourney was the first to deploy AI image-to-video generator, competing with Openai's Sora, Google's Veo 3, Adobe's Firefly and more.

Called V1, the tool is currently only available to desktop users via Midjourney's Discord app, so you will need to sign up for at least a 10-month subscription for your company to begin using the service.

Users can press “Animation” to move images generated in Midjourney. V1 creates a set of four 5-second videos based on input.

There are two animation settings to choose from: “Auto” and “Manual”. With the “automatic” setting, the tool creates what the startup calls “motion prompts” and creates “just move things.” But if you're looking for a little more creative control, the “manual” animation buttons can explain how the user wants things to work and how the scene develops.

The V1 also offers two styles: high motion and low motion. At low movements, the camera stays almost static, but subjects move slowly and deliberately. In high motion, both the subject and the camera move, but Midi Johnny admits that “all of these movements can lead to unstable mistakes.”

Additionally, users can animate images uploaded from outside of MidJourney. You will need to drag the image you want to animate into the prompt bar, mark it as “Start Frame”, enter a motion prompt, and explain how to move it. Once you get the video you want to keep, you can “expand” in about 4 seconds, with a total of about 4 times.

But it's not cheap to direct your creative aspirations on a video. Generating videos using MidJourney costs eight times more than traditional image generation. This means burning monthly credits much faster than usual.

Also, there is no guarantee that at this early stage the tool will ultimately cost you. Midjourney said the cost of running these models is “hard to predict” and that it monitors how people ensure they run “sustainable business” before adjusting pricing.

New features come with new features as Midjourney is loaded on many plates to address beyond product design. Last week, Universal and Disney sued Bay Area startups, claiming that the business is a “bottomless hole in plagiarism” as a result of drawing from many iconic productions for its images.

However, the lawsuit has not stopped startups from making very ambitious declarations about the future of their technology. “We believe that this technology's inevitable destination is a model that allows for real-time open-world simulation,” a Midjourney spokesman said as part of the announcement.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *