How a lot element is an excessive amount of? Midjourney v6 makes an attempt to search out out

In December, simply earlier than Christmas, Midjourney launched an alpha model of its newest picture synthesis mannequin, Midjourney v6. Over winter break, Midjourney followers put the brand new AI mannequin via its paces, with the outcomes shared on social media. To this point, followers have famous rather more element than v5.2 (the present default) and a special strategy to prompting. Model 6 may also deal with producing textual content in a rudimentary manner, but it surely’s removed from good.

“It is positively a loopy replace, each in good and fewer good methods,” artist Julie Wieland, who steadily shares her Midjourney creations on-line, instructed Ars. “The main points and surroundings are INSANE, the draw back (for now) are that the generations are very excessive distinction and overly saturated (imo). Plus it’s worthwhile to form of re-adapt and rethink your prompts, working with new buildings and now much less is form of extra when it comes to prompting.”

On the similar time, critics of the service nonetheless bristle about Midjourney coaching its fashions utilizing human-made paintings scraped from the online and obtained with out permission—a controversial observe frequent amongst AI mannequin trainers we now have lined in element prior to now. We have additionally lined the challenges artists would possibly face sooner or later from these applied sciences elsewhere.

An excessive amount of element?

With AI-generated element ramping up dramatically between main Midjourney variations, one may surprise if there’s ever akin to factor as “an excessive amount of element” in an AI-generated picture. Midjourney v6 appears to be testing that very query, creating many photographs that typically appear extra detailed than actuality in an unrealistic manner, though that may be modified with cautious prompting.

In our testing of model 6 (which might at present be invoked with the “–v 6.0” argument on the finish of a immediate), we seen occasions when the brand new mannequin appeared to provide worse outcomes than v5.2, however Midjourney veterans like Wieland inform Ars that these variations are largely because of the totally different manner that v6.0 interprets prompts. That’s one thing Midjourney is constantly updating over time. “Previous prompts typically work a bit higher than the day they launched it,” Wieland instructed us.