Get all your news in one place.
100’s of premium titles.
One app.
Start reading
Tom’s Guide
Tom’s Guide
Technology
Ryan Morrison

Midjourney v6.5 could be out ‘by the end of the month’ with improved realism and skin textures

Midjourney.

Midjourney is one of the most advanced, photorealistic artificial intelligence image generators available today and it's about to get even better when version 6.5 is released. With this new update, we’ll get improved realism and better skin textures — and it could launch this month.

According to a post on X by AI art expert Nick St. Pierre, Midjourney CEO David Holz said during the most recent “office hours” that work was progressing on the new update.

Holtz told people on the call that v6.5 will come with improved image clarity as well as improvements to specific areas such as hand quality and skin textures. As well as upgrades to the model there will be improvements to the web app and personalization.

AI artist Alie Jules, who also tuned in for the call, reported on X that the first release will likely be in alpha for a select number of users while they stress test the update, rather than broadly available. This is in line with previous releases and a common approach for AI companies.

What can we expect from Midjourney 6.5?

Prompt: "Realistic amateur smartphone photo, iPhone SE 2020, candid of a woman in her late 20s, wearing a floral dress, sitting on a park bench, caught off-guard while looking at her phone, no bokeh effect, everything in focus from foreground to background, wide depth of field, fountain clearly visible in the background, natural lighting with harsh midday shadows, slight overexposure in highlights, some image noise in darker areas, lens flare from bright sky, imperfect framing with part of bench cut off, typical smartphone camera limitations --v 6 --ar 16:9" (Image credit: Midjourney/Future AI image)

Each new Midjourney update brings with it certain features or changes to the model that weren't previously available in earlier versions. For example, version 6 brought with it better text rendering and significant improvements to photo-realism.

I suspect with 6.5 we'll see more of that with improvements to specific pixel quality and density as well as updates to the way the model renders skin and facial tones. This would allow for the creation of even more realistic-looking humans. Something Midjourney already does better than any other model I’ve tried.

In earlier office hours, Holtz suggested the next iterative update could be split into two, focusing on pixel quality in one and then hand and body coherence in the next, but it appears they are now working on a single 6.5 release.

Other updates likely in 6.5 are improvements to text rendering. While this got better with v6 it isn’t as accurate as other models like Ideogram, Phoenix from Leonardo or even DALL-E 3.

What else came out during office hours?

The prompt: "Realistic amateur smartphone photo, Motorola Moto G Power, unposed group of friends in their early 20s, having a picnic on a grassy hill, city skyline in the distance, no bokeh effect, all faces and scenery in focus, wide depth of field, lens flare from sun, slightly washed-out sky, some digital zoom artifacts, uneven exposure with darker foreground, visible noise in shadow areas, caught mid-conversation with some awkward expression --v 6 --ar 16:9" (Image credit: Midjourney/Future AI image)

As well as updates to the progress on 6.5, Holtz also confirmed that they are still working on version 7, currently focusing more on the speed of generation and a completely clean slate for the personalization feature.

Personalization was introduced earlier this year to allow users to customize the way the model generates images based ont heir own preferences.

Holtz also confirmed they haven’t started the final training run for v7 and that it will need to go through testing and other tasks before release — so there’s no date available yet.

Other updates include the fact that they're running behind on building a style exploration tool but they may work on a simpler solution just to give people an idea of the many many styles available within Midjourney more quickly.

The update also confirmed 3D and video models are still in development but they may take some time, particularly video, as Midjourney is taking a more detailed approach that allows for better control and realism than current transformer diffusion models.

More from Tom's Guide

Sign up to read this article
Read news from 100’s of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.