Midjourney, a pioneering AI image-generating service, has unveiled its first new AI image model in nearly a year, marking a significant milestone in its development.
The new model, dubbed V7, began rolling out in alpha around midnight Eastern on Thursday, shortly after OpenAI introduced a new image generator in ChatGPT that quickly gained popularity for its ability to create Ghibli-style photos. Although Midjourney’s V7 is not specifically designed for Ghibli-style images, it nonetheless produces visually appealing works, as observed by this reporter.
To utilize V7, users must first create a Midjourney “personalization” profile by rating approximately 200 images, unless they have already done so. This profile enables the model to tailor its output to individual visual preferences, and V7 is the first Midjourney model to have personalization enabled by default.
Once the profile is set up, users can access V7 on Midjourney’s website or, if they are part of the Midjourney Discord server, through the Discord chatbot. The web app allows users to 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. He further elaborated on the model’s capabilities in a Discord announcement, stating that V7 is “much smarter with text prompts” and produces images with “noticeably higher” quality, featuring “beautiful textures” and improved coherence in details such as bodies, hands, and objects.
V7 is available in two versions, Turbo and Relax, with the former being more costly to run. The model also powers a new tool called Draft Mode, which renders images at 10 times the speed and half the cost of the standard mode. Although Draft images are of lower quality than those produced in standard mode, they can be enhanced and re-rendered with a single click.
Midjourney has begun the alpha-test phase of its new V7 image Model, which is its “smartest, most beautiful, most coherent model yet.” The company invites users to try it out and expects to release updates every week or two over the next two months. pic.twitter.com/Ogqt0fgiY7
— Midjourney (@midjourney) April 4, 2025
Several Midjourney features are not yet available for V7, including image upscaling and retexturing, according to Holz. However, these features are expected to be added in the near future, possibly within the next two months.
Holz emphasized that V7 is “an entirely new model with unique strengths and probably a few weaknesses” and encouraged users to experiment with it, providing feedback on its capabilities and limitations.
Source Link
