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?
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.
Midjourney V6.1 is now live! V6.1 greatly improves image quality, coherence, text, and comes with brand-new upscaling and personalization models. It’s smarter, faster, clearer, and more beautiful. We hope you enjoy our best model yet <3 pic.twitter.com/4qfervgbhMJuly 30, 2024
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?
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.
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.
