EWEEK content and product recommendations are editorially independent. You can earn money by clicking on the link to your partner. learn more.
Midjourney, the AI platform best known for its impressive image generation, has expanded into the video space. On Wednesday, the company unveiled its first-ever video generation model called the V1. This image-to-video tool converts still images into short animation clips.
The launch of V1 marks a pivotal moment for Midjourney. This has focused primarily on still images since its inception. In a company's post about the release of V1, Midjourney founder David Holz said: (3D model) And you need to be able to do all this at high speed (real-time model). ”
How Midjourney V1 works
V1 uses a simple “image to video” process. Users can create images within MidJourney or upload images from external sources. The user then clicks on the animation to convert it to a video. The user can then assign a “start frame” and provide a “motion prompt” to guide how the scene works.
Two animation modes are available. The “Auto” setting provides a default “motion prompt” to keep things moving. For more control, the “Manual” animation buttons allow users to accurately explain how scenes and objects are moved.
This model also includes “high movement” and “low video” modes. Lower movements are recommended for subtle movements and surrounding scenes where the majority of the camera remains static. High movement is ideal for dynamic scenes with important subject and camera movement. High motion can be exciting, but Midi Johnny advises, “All of these moves can lead to erratic mistakes.”
Each video starts as a 5-second clip. Users can expand the clips for up to four times, approximately 4 seconds per segment.
How to access Midjourney V1
According to Midjourney, each video generation job requires eight times more computing power than standard images, which translates to the cost of about one image per second in the video.
Currently, access is limited to web users with active Midjourney subscriptions starting at $10 per month. Midjourney claims that the tool is up to 25 times more affordable than other AI video tools.
How Midjourney's V1 stands out among its competitors
The market for generating AI video tools is rapidly increasing its competitiveness. Competitors include Openai's SORA, Google's VEO 3, Adobe's Firefly, and Runway's Gen-4, all pushing the limits of text and imagery into the video.
Midjourney's tools are more casual and user-friendly compared to film-like and photorealistic models. The V1 is still not comparable to its competitors' Polish language, but ease of use and relatively low cost can make it attractive to artists, designers and curious enthusiasts.
How Midjourney responds to Disney/Universal lawsuits
Last week, Disney and NBCuniversal filed a copyright infringement lawsuit against Midi Johnny. The complaint alleges that Midjourney's AI model was trained with protected content and created illicit digital versions of iconic characters such as Darth Vader and Homer Simpson.
Midjourney does not issue a direct response to the lawsuit, but continues to encourage users to “use these technologies responsibly” and reflects their long-standing attitude towards the use of ethical AI.
Read the detailed comparison of Eweek Midjourney vs. Dall-E.
