Midjourney 5 improves almost every aspect of AI generated images

Cal Jeffrey

Posts: 3,785   +1,207
Staff member
Getting better: With all the recent news revolving around ChatGPT and other large language models, it's easy to forget that their cousins—AI image generators—are still improving. One may have figured out how to render eyes and hands without making the subject look like something from a nightmare. however, the results still creep some people out.

Earlier this week, research lab Midjourney released a beta for version 5 of its self-named AI-imaging software. According to its announcement via Twitter, the latest version adds higher picture quality, more "diverse" results, a more expansive range of styles, seamless textures, and much more.

Users have already posted hundreds of stunning results, and feelings about the improvements are mixed. Most are impressed because imaging AI has struggled to produce aspects like shadows, reflections, eyes, and hands. Below is an image we created with OpenAI's Dall-E as an example of where the machine has trouble.

The composition is somewhat off, and the general feel is cartoonish. The lighting is all wrong. The eyes and hands are badly deformed. The legs are fouled with artifacts, as are the popcorn container and the seat next to the subject. This result is one of four with similar problems to varying degrees.

Version 5 of Midjourney seems to have improved in this respect, at least from the examples others have shared. The results from simple prompts border on the uncanny valley—realistic enough to pass as professional photos in many cases, but still with that odd quality you can't quite place. While incredibly realistic, many have described the images as creepy.

Our own Kishalaya Kundu said, "I'm more afraid than impressed, to be honest," after viewing a series of nearly flawless Midjourney V5 photos. The fear being that one could fairly easily create a fake image and pass it off as genuine.

Creep factor aside, compared to V4, Midjourney V5 has dramatically improved quality. Graphic designer Julie Wieland has used Midjourney V4 (released last November) for some time and says that version 5 has "incredibly realistic" skin textures. The lighting effects are also much better, including reflections, glare, and shadows. Perhaps most importantly, the AI generates hands and eyes that appear natural most of the time.

"Eyes are almost perfect and not wonky anymore," Wieland told Ars Technica. "Hands are correct most of the time, with five fingers instead of 7-10 on one hand. MJ v5 currently feels to me like finally getting glasses after ignoring bad eyesight for a little bit too long. Suddenly you see everything in 4k; it feels weirdly overwhelming but also amazing."

Midjourney also improved the native resolution from 512x512px to 1024x1024px. The increase aligns it with Dall-E. However, Version 4 could supersample to double the native resolution. It's not unreasonable to expect V5 to use the same technique to produce 2048x2048 images, but that is for an update further down the road.

The bottom line is MidJourney only hit the AI scene one year ago. Many (not all) of these images flooding Twitter feeds this week are untouched. Previously, Weiland used a combination of techniques to improve Midjourney 4's visual quality, including "outpainting" with Dall-E and touchups in Photoshop. Version 5 promises less post-generation editing and perhaps photo-perfect images sooner than we can imagine. This prospect is indeed both exciting and frightening.

Permalink to story.



Posts: 546   +1,034
Midjourney is very good when compared to Dall-E. However, till last month I was getting several artifacts like the aforementioned warped hands and faces in Midjourney too esp when scene comprised of two or more people.
Also tried to generate some images with texts. The results were awful.

Not belittling the progress, just pointing the reality as the result will not be nearly as good as it's hyped up to be, except for portraits.
I'm struggling to see a useful purpose for this technology. Gaming? Visual ads? Porn?
Advertising is probably top of the list. Whether advertising is "useful".. that's probably debatable.
But, companies won't need to pay models extravagant salaries for ads(idk how much longer magazines will last, but internet ads at least?) or web adverts, you won't have to hire anyone for it, just have the AI make it


Posts: 225   +163
What could go wrong, I mean they could catch you robbing a bank in Manhattan and assassinating someone in China all at the same time with Video Evidence...what would go wrong....I cant see a problem with that if your a Nazi Dictator who wants to kill of people without a cause


Posts: 580   +398
I can see where this leads........ to paid version of Midjourney that takes your textual input and produces very accurate and realistic porn.