On June 22, Midjourney announced the release of version 5.2.
The latest update to the program since the company announced the release of V5.1 in May, V5.2 comes with several exciting updates and features that artificial intelligence art enthusiasts are already experimenting with in creative ways. The upgrade can yield some impressive results, but like any tool, it works best when you have an understanding of its capabilities and limitations.
Here’s everything you need to know about the V5.2 model and its new toolset.
How to set up the new version?
If you want to play with V5.2, you don’t need to do anything to set it up; model updates are automatically downloaded to user settings and will take effect as soon as you input a command.
Midjourney’s Zoom Out function
Similar to Adobe’s generative fill tools, the Zoom feature allows users to expand an original image, enlarging the scope to a wider scale while preserving the identity of the original image details. After entering instructions using the command “/image,” Midjourney will offer four visual iterations based on the user’s input. They can then “enhance” the specific image they like the most and process it in higher detail.
Users will now see three buttons below the enlarged image labeled “Zoom Out 2x,” “Zoom Out 1.5x,” “Custom Zoom.” While the first two will enlarge the original scene by two and a half times the size of the original image, respectively, the “Custom Zoom” will allow you to adjust this ratio (through a simple manual instruction) to anything between 1.0 and 2.0.
The fun part of playing here is the infinite possibilities of zoom. If you shrink your output, you can capture the enlarged image and reapply the Zoom Out 1.5/2x feature as many times as you want, and it will continue to be based on your expanding image.
Square feature function
The update also comes with a “Make Square” tool, which changes the shape of images made with a non-perfect square aspect ratio. You can expand landscape images (made with the finishing instruction -ar 16:9) vertically using the tool and vice versa. Look for the arrows next to the “Make Square” button, indicating the direction of the size change.
Variation Mode function
Midjourney V5.2 also comes with a new feature called “Variation Mode” that essentially allows users to sharpen the visual nuance and change they want to apply to their outputs. Use the “/settings” command to set this feature to either “High Variation Mode” or “Low Variation Mode”.
High variation leads to a slightly greater visual deviation from the original output, which may result in more interesting and original results, while keeping the setting low will tend to allow for much greater visual consistency.
The following examples use the same visual seed and instruction, with the left outputs originating from “Low Variation” and the right defined as “High.”
Midjourney now also offers a more localized version of this feature when enlarging an image, allowing you to “Strengthen” or “Softly” change a single output. This is similar in function to the Variation Mode, but it allows you to apply the tool in specific cases without affecting all of your work. If you truly want to experiment, combine “High Variation Mode” with “Strengthen (Strong)” for the best results.
Stylize function
Midjourney is trained to create images with artistic flair and visual aesthetics, setting it apart from programs like Stable Diffusion. One way users can leverage this effect is through the “Stylize” function. While users could previously add “-stylize X” to the end of their instructions (where X ranges from 0-1000), V5.2 has taken the existing stylize capabilities of the model and elevated them to an 11 in terms of realism and artistry. Here are just some of the images people are creating using the new model:
Subscribe to our newsletter and stay updated on everything new in the world of artificial intelligence.
