Midjourney, one of the earliest AI image-generating services on the web, has released its first new AI image model in nearly a year.
Dubbed V7, the model began rolling out in alpha around midnight ET on Thursday, comes a week after OpenAI debuted a new image generator in ChatGPT that quickly went viral for its ability to create Ghibli-style photos.
Midjourney’s is not a Ghibli-optimized model, though — at least not officially — but it nonetheless can generate aesthetically pleasing works, at least to this reporter’s dilettante eye.
We’re now beginning the alpha-test phase of our new V7 image Model. It’s our smartest, most beautiful, most coherent model yet. Give it a shot and expect updates every week or two for the next two months. pic.twitter.com/Ogqt0fgiY7
— Midjourney (@midjourney) April 4, 2025
To use it, you’ll first have to rate around 200 images to build a Midjourney “personalization” profile, if you haven’t already. This profile tunes the model to your individual visual preferences; V7 is Midjourney’s first model to have personalization switched on by default.
Once you’ve done that, you’ll be able to turn V7 on or off on Midjourney’s website and, if you’re a member of Midjourney’s Discord server, on its Discord chatbot. In the web app, you can quickly select the model from the drop-down menu next to the “Version” label.
Midjourney CEO David Holz described V7 as a “totally different architecture” in a post on X.
“V7 is … much smarter with text prompts,” Holz continued in an announcement on Discord. “[I]mage prompts look fantastic, image quality is noticeably higher with beautiful textures, and bodies, hands, and objects of all kinds have significantly better coherence on all details.”
V7 is available in two flavors, Turbo (costlier to run) and Relax, and powers a new tool called Draft Mode that renders images at 10x the speed and half the cost of the standard mode. Draft images are of lower quality than standard-mode images, but they can be enhanced and re-rendered with a click.
A number of standard Midjourney features aren’t available yet for V7, according to Holz, including image upscaling and retexturing. Those will arrive in the near future, he said, possibly within two months.
“This is an entirely new model with unique strengths and probably a few weaknesses” Holz wrote on Discord. “[W]e want to learn from you what it’s good and bad at, but definitely keep in mind it may require different styles of prompting. So play around a bit.”
In my brief testing, V7 adhered reasonably well to my prompts, though I didn’t have time to really put the model through the ringer.
Midjourney is an unusual operation. Started in 2022 by Holz, who co-founded PC peripheral company Leap Motion, it hasn’t raised a dime of outside money.
In late 2023, Midjourney was reportedly expecting to bring in around $200 million in revenue. Recently, the San Francisco-based firm said it was establishing a hardware team to work on some projects that it did not detail, and it continues to train previously announced models for video and 3D object generation.
The company is facing several lawsuits that accuse it of infringing on the rights of millions of artists by training AI tools on images scraped from the web without the consent of the images’ creators.
