The popular Midjourney imaging neural network has been updated to version 5.1, eliminating several shortcomings at once and improving the overall quality of generated images.
Midjourney showed off a new version of its generative neural network. Update number 5.1 fixes a number of issues and, as the developers say, increases the overall level of creativity of artificial intelligence. The new version of Midjourney is now available to all subscribers to the service.
One of the main problems with generative neural networks has always been generating the correct number of fingers; we talk about this in more detail in a special comparison article. Midjourney 5.1 takes a big leap in this direction, significantly reducing the amount of manual build bugs, as you can see in the image above.
Also, the developers at Midjourney promise that 5.1 will produce sharper images with fewer “inconsistencies” within a single image. The neural network is also expected to learn to better understand short queries by thinking through the details on its own. Users who want more controlled results can turn on “RAW” mode, which means fewer image surprises.
Author:
Grigory Shcheglov
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
