Midjourney, one of many earliest AI image-generating companies on the internet, has launched its first new AI picture mannequin in almost a yr.
Dubbed V7, the mannequin, which started rolling out in alpha round midnight Japanese on Thursday, comes every week after OpenAI debuted a brand new picture generator in ChatGPT that shortly went viral for its potential to create Ghibli-style photographs. Midjourney’s just isn’t a Ghibli-optimized mannequin — a minimum of not formally — however nonetheless generates aesthetically pleasing works, a minimum of to this reporter’s dilettante eye.
To make use of it, you’ll first need to price round 200 photos to construct a Midjourney “personalization” profile in case you haven’t already. This profile tunes the mannequin to your particular person visible preferences; V7 is Midjourney’s first to have personalization switched on by default.
When you’ve accomplished that activity, you’ll be greeted with a togglable V7 on Midjourney’s web site and, in case you’re a member of Midjourney’s Discord server, on its Discord chatbot. Within the internet app, you may shortly choose the mannequin from the drop-down menu subsequent to the “model” label.
Midjourney CEO David Holz described V7 as a “completely completely different structure” in a submit on X.
“V7 is […] a lot smarter with textual content prompts,” Holz continued in an announcement on Discord. “[I]mage prompts look implausible, picture high quality is noticeably greater with lovely textures, and our bodies, palms, and objects of all types have considerably higher coherence on all particulars.”
V7 is obtainable in two flavors, Turbo and Calm down — the previous of which is extra expensive to run — and powers a brand new software referred to as Draft Mode that renders photos at 10x the pace and half the price of the usual mode. Draft photos are lower-quality than standard-mode photos, however may be enhanced and re-rendered with a click on of the mouse.
We’re now starting the alpha-test section of our new V7 picture Mannequin. It’s our smartest, most lovely, most coherent mannequin but. Give it a shot and count on updates each week or two for the subsequent two months. pic.twitter.com/Ogqt0fgiY7
— Midjourney (@midjourney) April 4, 2025
Various Midjourney capabilities aren’t accessible but for V7, in keeping with Holz, together with picture upscaling and retexturing. These will arrive within the close to future, he mentioned — presumably as quickly as inside two months.
“That is a wholly new mannequin with distinctive strengths and doubtless a couple of weaknesses” Holz wrote on Discord. “[W]e need to be taught from you what it’s good and unhealthy at, however undoubtedly take note it might require completely different kinds of prompting. So mess around a bit.”
In my temporary testing, V7 adhered fairly properly to the prompts I gave it. Granted, I didn’t have time to actually put the mannequin via the ringer.
Midjourney is an uncommon operation. Began in 2022 by Holz, who co-founded PC peripheral firm Leap Movement, it hasn’t taken a dime of out of doors cash.
In late 2023, Midjourney was reportedly anticipating to herald round $200 million in income. Just lately, the San Francisco-based agency mentioned that it was establishing a {hardware} staff to work on undisclosed tasks, and it continues to coach beforehand introduced fashions for video and 3D object technology.
A number of lawsuits accuse Midjourney of infringing on the rights of thousands and thousands of artists by coaching AI instruments on photos scraped from the online with out the consent of the photographs’ creators.
