Skip to main content

Midjourney v5 language model update adds realism to human hands

Midjourney v5 is the latest language model of the popular text-to-image generator known for its realistic creations.

The update rolled out to Midjourney’s paid customer base on Wednesday and many users, including Graphic designer Julie Wieland, have been sharing their new AI-generated artwork. AI details that the v5 language model brings with it include improved “efficiency, coherency, and quality,” Midjourney said on its website.

Related Videos

Just a heads-up – Midjourney's AI can now do hands correctly. Be extra critical of any political imagery (especially photography) you see online that is trying to incite a reaction. pic.twitter.com/ebEagrQAQq

— Del Walker (@TheCartelDel) March 16, 2023

Many users have especially noted the upgrades in the human hand details, with subjects more likely to have five fingers per hand. In previous models, human hands were often generated with an incorrect number of digits, anywhere from four to between seven and ten. Those who have been able to test Midjourney v5 have been impressed with the visual upgrades.

“The latest Midjourney v5 model is both extremely overwhelming/scary and beyond fascinating,” Wieland told PetaPixel.

“Its ability to recreate intricate details and textures, such as realistic skin texture/facial features and lighting, is unparalleled,” she added.

While Midjourney is a somewhat unique language model, it works in a similar fashion to other text-to-image generators such as Stable Diffusion and DALL-E, using worded prompt descriptors to create images, as per the model, which is trained using human-made art as a reference, according to ArsTechnica.

There has been an ongoing debate about whether AI-generated art is legal or ethical; however, many Midjourney v5 users consider with continued upgrades it might be indistinguishable from real art and photography. Wieland considers that AI image generators, such as Midjourney are likely to be companions for photographers rather than replacements.

Midjourney v5 is here! (for real this time, lol)

Here are some side-by-sides of my prompts, v4 vs v5, as well as some new prompts and crowd shots. I'll add more to this as I experiment.

🧵 pic.twitter.com/qSEZWQBXou

— Nick St. Pierre (@nickfloats) March 15, 2023

However, Midjourney v5 isn’t without its flubs. AI image creator Nick St. Pierre shared many of his works, for which he used the same prompts in the previous Midjourney v4 and Midjourney v5. One image was a fascinating shot of young women in 1960s street style that resembles an outdoor fashion shoot. Upon closer inspection, you can spot the floating hands not attached to bodies and misshapen faces in the background.

With its latest v5 model, Midjourney founder David Holz recommended on the brand’s Discord that users shy away from short prompts in favor of “longer, more explicit text” to get better results.

Editors' Recommendations

Can A.I. beat human engineers at designing microchips? Google thinks so
google artificial intelligence designs microchips photo 1494083306499 e22e4a457632

Could artificial intelligence be better at designing chips than human experts? A group of researchers from Google's Brain Team attempted to answer this question and came back with interesting findings. It turns out that a well-trained A.I. is capable of designing computer microchips -- and with great results. So great, in fact, that Google's next generation of A.I. computer systems will include microchips created with the help of this experiment.

Azalia Mirhoseini, one of the computer scientists of Google Research's Brain Team, explained the approach in an issue of Nature together with several colleagues. Artificial intelligence usually has an easy time beating a human mind when it comes to games such as chess. Some might say that A.I. can't think like a human, but in the case of microchips, this proved to be the key to finding some out-of-the-box solutions.

Read more
What is deep learning?
Curious how A.I. 'brains' work? Here's a super-simple breakdown of deep learning
History of AI neural networks

Deep learning is a particular subset of machine learning (the mechanics of artificial intelligence). While this branch of programming can become very complex, it started with a very simple question: "If we want a computer system to act intelligently, why don't we model it after the human brain?"

That one thought spawned many efforts in past decades to create algorithms that mimicked the way the human brain worked—and that could solve problems the way that humans did. Those efforts have yielded valuable, increasingly competent analysis tools that are used in many different fields.
The neural network and how it's used

Read more
MIT’s latest A.I. is freakishly good at determining what’s going on in videos
mit algorithims predicts whats happening in video gettyimages 200553945 001

How a Temporal Relation Network understands what's going on there

Just a few frames of information telling a story are all we need to understand what is going on. This is, after all, the basis for comic books -- which provide just enough of the important story beats for us to follow what has happened. Sadly, robots equipped with computer vision technology struggle to do this. Until now, at least.

Read more