Midjourney is in the final testing stages of V7, a significant update that rebuilds almost every part of the AI ​​image generator system.

During an office hours session this week, developers explained that version 7 features a new architecture, different data sets, and revised language processing methods.

Internal testing may take from a week to a month, followed by a two-week adjustment phase and a potential alpha period with limited features.

“The V7 model is a comprehensive overhaul of V6, including new architecture, different datasets, and revised language processing methods,” Midjourney Announce On its official server. “The alpha period often follows the initial configuration, with limited features enabled.”

While the extensive rework of V7 continues, the Midjourney team is also exploring video creation possibilities through multiple approaches, including developing their own video model or partnering with third-party providers.

The main challenge, according to the team, is to make video creation user-friendly and cost-effective.

The team has not revealed a specific timeline for this video generator, so it may be in an earlier development stage. The developers are currently working to "balance speed, cost and production quality," according to the announcement.

About 85% of users prefer images created using the platform's personalization system, which now includes mood boards and multiple profiles, Medjorney said. The company plans to expand these features by combining mood boards with style reference capabilities.

The platform also plans to offer two distinct generation modes: a “Real Time” option for quick results similar to dead The Visualization feature, or the Doodle to Image feature in Krea AI, or the Leonardo Realtime Canvas.

They are also working on a high-capacity mode to create large sets of images similar to Leonardo's flow state.

Midjourney V6 was released in December 2023 It delivered better results than its immediate predecessor, Midjourney V5.1, which was released in May 2023.

The results were noticeable, but the step from V5 to V6 was not as significant as the upgrade from V4 to V5. It was midway through the trip More careful Speaking of the V6, it's reasonable to think that the team is so satisfied with the results that they're calling this new version a "total overhaul."

During that period, the team also announced their entry into the AI ​​hardware market but have not revealed more details yet.

Since the release of Midjourney V6, the team has done just that Expanded its capabilitiesAnd adding features such as image editor, standalone interface, style customization tool, external drawing, image enlargement, etc.

The team also started paying attention to user feedback, sharing various polls to ask what features users would like to implement.

according to Decryption Analysis,Midjourney currently excels at creating creative AI images,,consistently producing highly aesthetic results that stand out,among its competitors.

Although it may sometimes sacrifice strict immediacy and accuracy of text presentation, its versatility and comprehensive capabilities make it a powerful tool.

The addition of customizable styles has enhanced its appeal, allowing users to create unique and personal images that differ greatly from the platform's signature look.

Modified by Sebastian Sinclair