On Thursday, Midjourney unveiled version 5.2 of its AI-powered photomontage model, which includes a new “zoom out” feature that allows a central composite image to be preserved while automatically creating a larger scene around it, simulating zoom out using a viewfinder.
Similar to outsourcing — AI image technology OpenAI’s DALL-E 2 was introduced in August 2022 — Midjourney’s Zoom Out feature can take an AI-generated image and expand its boundaries while keeping its original subject centered on the new image. But unlike DALL-E and Photoshop, you can’t select a custom image to enlarge it. Currently, Minimize v5.2 only works on images created within Midjourney, a subscription AI image creation service.
On the Midjourney Discord server (it remains the official interface for Midjourney, though there are plans underway to change this), users can experiment with minification by creating any v5.2 image (now the default) and upscaling the score. After that, special “Zoom” buttons appear below the output. You can zoom out by a factor of 1.5x, 2x, or a custom value between 1 and 2. Another button called “Make Square” will create a texture around the current image in such a way that it creates a square aspect ratio of 1:1.
Midjourney creator David Holz announced new features and improvements v5.2 on his Discord server Thursday night. Aside from “Reduce”, the more significant additions include the aesthetic overhaul system, which promises better image quality and a stronger “Style” command that effectively affects how unreal the image looks. There’s also a new “High Contrast Mode”, activated by default, that increases compositional diversity between image generations. In addition, the new “/shorten” command allows users to rate prompts in an effort to cut out unnecessary words.
Despite the immediate launch of version 5.2, Holz emphasized in his announcement that changes may occur without notice. Older versions of Midjourney are still available using the “/settings” command or the “-v 5.1” command argument on the line.
For fans of this new art form of photomontages that proponents like Julie Weiland sometimes call “montage,” the changes in version 5.2 are welcome changes, with some Midjourney users calling them “a surprise” And “Brainstorming,” which isn’t an out of the ordinary formula in the hype-friendly world of AI right now. But fans will likely argue that Midjourney’s visual improvements justify the incredible awesomeness. interactions among them.
The latest update is part of a series of quality improvements since March 2022, when the model produced relatively undefined images that lacked detail. Most recently, Midjourney introduced v5.0 in March and v5.1 in May this year, both of which improved realism and image detail. The introduction of the v5 series of mockups allowed the creation of photorealistic images of Pope Francis and Donald Trump sparking concerns about deepfakes on social media.
Despite the excitement over the new features among Midjourney fans, photomontage remains controversial among some artists because of how these AI systems are trained, using millions of images pulled from the web without the artist’s consultation, credit, or permission. Midjourney has never officially disclosed the exact contents of its training data. Adobe is trying to take a more ethical path moving forward with Firefly, but Venture Beat recently reported that active artist consent remains marginal.
Right now, it’s hard not to appreciate the technical advances Midjourney has unlocked while still wondering if there might be a more ethical path forward with this technology—one that would satisfy artists, both traditional and musicians alike.