Midjourney 6 Consistent Styles feature and updates this week

At the latest weekly office hours briefing, Midjourney has announced a series of updates that are set to enhance the experience for its users. The highlight of these updates is the introduction of version 6 Beta, which promises to deliver improved image quality and a more user-friendly interface. This new version is designed to make the creative process smoother and more intuitive, allowing users to focus on bringing their ideas to life.

One of the most exciting developments is the expansion of the alpha creation website, which now includes a new explore page. This feature provides users with a wider array of top images to draw inspiration from, going beyond the personalized feed that users are accustomed to. It’s a move that’s expected to spark creativity and provide fresh perspectives for users’ projects.

Midjourney Consistent Styles

Midjourney also late last night announced the release of the first algorithms for ‘Consistent Styles’ today. Midjourney are calling the feature “Style References“. They have been specifically designed to work similarly to image prompts where you give a URL to one or more images that ‘describe’ the consistent style you want to work over. This tool is aimed at helping users maintain visual consistency when generating a series of images or working on thematic collections. It’s a valuable asset for those who want to ensure that their work aligns with their artistic vision and remains cohesive throughout.

How to use Midjourney Style References :

  • Type --sref after your prompt and put one (or more) URLs to images like this --sref urlA urlB urlC
  • The image model will look at the image urls as ‘style references’ and try to make something that ‘matches’ their aesthetics
  • Set relative weights of styles like this --sref urlA::2 urlB::3 urlC::5
  • Set the total strength of the stylization via --sw 100 (100 is default, 0 is off, 1000 is maximum)
  • Regular image prompts must go before --sref like this/imagine cat ninja ImagePrompt1 ImagePrompt2 --sref stylePrompt1 stylePrompt2
  • This works for both V6 and Niji V6 (it does not work with V5 etc)
See also  Everything You Need to Know About Green Technology in 2023

The Midjourney team explain :

  • We’ll likely update this in the next few weeks (and it may change things so be careful while it’s all in alpha).
  • If your prompt tends towards photorealism and you want a conflicting style like illustration you may still need to add some text to your prompt saying so
  • Style References have no direct effect on image prompts, only on jobs that contain at least one text prompt
  • Our plan will be to add a “Consistent Character” feature at later date that works the same with a --cref argument.

Midjourney updates this week

Here are some other articles you may find of interest on the subject of Midjourney styles and AI art creation :

Midjourney has also made improvements to the “describe” function, which is designed to better understand user prompts. This enhancement means that users will have to spend less time tweaking their prompts and can instead dedicate more time to the creative aspects of their projects.

For those who enjoy creating characters, the updates to the Niji model are particularly noteworthy. New features such as pan, zoom, and in-painting, as well as improvements in facial consistency, will make it easier for users to maintain the identity of their characters across different images. This is a significant step forward for anyone involved in narrative and character design.

The platform’s website itself is being redesigned to provide a more streamlined and accessible experience. This redesign is a response to community feedback and focuses on incorporating features that have been in high demand. The aim is to make the platform more intuitive and user-centric.

See also  Google AdSense moves to per-impression payments for publishers

During the event, there was also a thoughtful discussion about artistic nudity, highlighting Midjourney’s commitment to balancing creative expression with community standards. This indicates that the platform is considering the diverse needs and values of its user base.

Looking ahead, Midjourney has announced that future updates will include improved text rendering, the ability to create images with transparent backgrounds, and more precise color control through hex code adjustments. These upcoming features are designed to give users even more control over their creative output, allowing for a level of precision that was previously unattainable.

The platform is also considering the addition of new features such as upscaling, seamless tiling, and the ability to export prompt history. These potential updates suggest that Midjourney is looking to broaden its appeal and cater to an even wider audience by expanding its capabilities.

The recent updates and the anticipation of future enhancements are a testament to Midjourney’s commitment to evolving in response to the needs of its community. The platform is clearly focused on improving image quality, making the user experience more accessible, and providing tools that enrich the creative process. For users, these changes are likely to make their creative journey more immersive and enjoyable, offering new possibilities for artistic expression and innovation.

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.

See also  Want to skip to the good bit of a video? YouTube is testing a smart AI feature for that

Leave a Comment