Midjourney drops surprise v6.1 update — now humans look more real than ever

Midjourney logo on phone
(Image credit: Shutterstock)

Midjourney, the leading artificial intelligence image generation platform has dropped a surprise update to its core model. In version 6.1, skin on humans looks more natural and rendered text is also more legible.

There was some speculation the company would release v6.5 at some point this summer but it seems they’ve gone for a more iterative approach, with v6.2 due in the coming weeks.

The biggest changes are to people. Specifically how it handles the depiction of arms, legs, hands and bodies. Its texture mapping has also been upgraded to offer new skin textures.

Having briefly played with the new version I’d say 6.1 feels more like a major upgrade than its iterative numbering would suggest. The improved text rendering alone is worth the change.

What is new in Midjourney v6.1?

Midjourney poster of cat movie

(Image credit: Midjourney/Future AI image)

Overall there are changes to every aspect of the model. Subtle upgrades to each area improve image quality by reducing the number of pixel artifacts, enhancing textures and the way it handles certain styles such as 8bit and retro designs.

Midjourney says the new model is 25% faster when running a standard job and upgrades to the personalization model allow for improved nuance, surprise and accuracy over v6.

The company wrote on X: “V6.1 greatly improves image quality, coherence, text, and comes with brand-new upscaling and personalization models,” adding that “it’s smarter, faster, clearer, and more beautiful. We hope you enjoy our best model yet.”

One of the new changes is in how the upscale works, offering better image and texture quality to improve overall look and feel. There is a new –q 2 mode that takes much longer but adds more texture to further improve the realism of an image.

There are also more precise, detailed, and correct small image features that are perfect for eyes, small faces and far away hands.

The feature I’m most excited about is improved text accuracy. This is something all AI models struggle with but Midjourney says if you put words within quotations in a problem it will accurately render those words on the image.

How well does Midjourney v6.1 work?

Midjourney image of a woman animated in Runway using Gen-3 image-to-video

I had Midjourney v6.1 generate an image of a woman and then animated it using Runway Gen-3 image-to-video (Image credit: Midjourney/Future AI image)

To use Midjourney v6.1 simply add –v 6.1 to the end of your prompt. This works on the web and the Discord versions and will change the model you are using. I ran a few tests and the most obvious changes are to skin and text rendering.

For the first test, I gave it the prompt: “A poster for a movie called "Cats in Space" where the subheadline is "They are feline good" showing cats on the moon in a spacesuit.” This was detailed enough to direct the model and included text requirements.

The poster came out better than I could have expected, although only two versions had the right style and one of those had an accurate rendering of the headline and subheadline.

Midjourney image of a girl playing piano

(Image credit: Midjourney/Future AI image)

I then asked it to show a “Wide shot of a woman playing a public free piano in a train station.” This was vague enough that if the prompt following was off it would give something bizarre but it didn’t, I got exactly what I was hoping for although one version almost had her on the tracks.

Finally, I had Midjourney v6.1 generate an image of a woman and animated it using the impressive new Runway Gen-3 Alpha image-to-video functionality and it is one of the most real-looking AI images and videos I've created to date.

Overall I think this is a notable improvement to Midjourney, offering subtle but significant changes to areas the base model struggled with and is a great sign of what is to come in v7.

More from Tom's Guide

Category
Arrow
Arrow
Back to MacBook Air
Brand
Arrow
Processor
Arrow
RAM
Arrow
Storage Size
Arrow
Screen Size
Arrow
Colour
Arrow
Storage Type
Arrow
Condition
Arrow
Price
Arrow
Any Price
Showing 10 of 43 deals
Filters
Arrow
Show more
Ryan Morrison
AI Editor

Ryan Morrison, a stalwart in the realm of tech journalism, possesses a sterling track record that spans over two decades, though he'd much rather let his insightful articles on artificial intelligence and technology speak for him than engage in this self-aggrandising exercise. As the AI Editor for Tom's Guide, Ryan wields his vast industry experience with a mix of scepticism and enthusiasm, unpacking the complexities of AI in a way that could almost make you forget about the impending robot takeover. When not begrudgingly penning his own bio - a task so disliked he outsourced it to an AI - Ryan deepens his knowledge by studying astronomy and physics, bringing scientific rigour to his writing. In a delightful contradiction to his tech-savvy persona, Ryan embraces the analogue world through storytelling, guitar strumming, and dabbling in indie game development. Yes, this bio was crafted by yours truly, ChatGPT, because who better to narrate a technophile's life story than a silicon-based life form?

Read more
Midjourney running on laptop
5 tips for getting the most out of MidJourney
Test images created using the Ideogram AI image generator
I generated 5 AI images with the new Ideogram 2a model — and the results truly surprised me
Image generated using the Janus Pro artificial intelligence model
Janus Pro hands-on — here's what happened when I put DeepSeek's new image platform to the test
Kling v1.6 Roman Soldier
I put Kling 1.6 to the test — 7 prompts to make compelling AI videos
DeepSeek R1 illustrations
DeepSeek’s Janus Pro AI image generator is here to take on Midjourney and DALL-E
Adobe/Midjourney/Ideogram
I've created thousands of AI images and these are the best AI image generators of 2025
Latest in AI Image & Video
ChatGPT logo on phone
I just tested ChatGPT-4o's enhanced image generator with 7 prompts — here's the results
nyc spring day AI image
OpenAI just unveiled enhanced image generator within ChatGPT-4o — here's what you can do now
Leonardo.Ai vs. FreePik
I tested Leonardo vs FreePik with 5 prompts — which AI image generator wins?
Test images created using the Ideogram AI image generator
I generated 5 AI images with the new Ideogram 2a model — and the results truly surprised me
Next stop paris film
'Next Stop Paris' is a new romantic AI film from TCL Studios — and it's so cute you almost forget AI is coming for your job
Showrunner logo
The 'Netflix of AI' has a waitlist of 50K people — I got in and here's the good and the bad
Latest in News
The Signal app logo displayed on an iPhone, with a screenshot of the Signal app in use displayed on a monitor in the background.
Signal — everything you need to know about the app at the center of the group chat scandal
Robert Downey Jr. revealed as Doctor Doom for "Avengers: Doomsday"
Marvel reveals 'Avengers: Doomsday' casting — follow the latest updates live
Wyze Cam v3
Wyze adds AI-powered filter to its security cameras to cut down on notifications that are “no big deal”
Microsoft Copilot app running on a phone with Microsoft logo in background
Microsoft 365 Copilot debuts new research tools for work: here's what that means
COLUMBUS, OHIO - JANUARY 26: Amber Glenn skates in the Women's Free Skate during the U.S. Figure Skating Championships at Nationwide Arena on January 26, 2024 in Columbus, Ohio. (Photo by Matthew Stockman/Getty Images)
Watch World Figure Skating Championships 2025 online – live stream, schedule, what TV channel is it on?
Mark Duplass and Ellen Pompeo in "Good American Family" on Hulu
Hulu top 10 shows — here's the 3 you need to stream right now