If we talk about artificial intelligence to create images based on a description, one of the best options currently available in Midjourney, one of the first AIs to hit the market and which, over the months, has been advancing by leaps and bounds.
A few weeks ago version 5 of Midjourney was released, a version that took a leap in quality Compared to the previous version, one of the main novelties is the possibility of interacting with this AI in a totally natural way, as if we were talking to a person and not a machine, without having to separate it with commas (although it can continue to be used). the concepts that we want to be reflected in the image that we want to obtain.
At that time, the head of this platform stated that they were working on version 6, although at the moment, it was not a priority, but rather that they wanted to optimize the operation of the current version. However, as expected, the first leaks about what Midjourney plans to implement in the next version of this AI to generate images have come to light.
What’s New in Midjourney V6
One of the main problems of all Artificial Intelligences that allow us to generate images based on a description is their final resolution, a resolution that, by default, is set to 512 and 1024 in width and height, a limitation that prevents them from being used larger without using an AI or applications that allow us to increase the resolution losing the minimum possible quality.
When we interact through Discord to obtain images with Midjourney, the images we obtain are 1024×1024, a resolution that, although it is true, is higher than the native one of Stable Diffusion, it is not enough for many uses. Midjourney version 6, will increase the resolution of the images that generates up to 2048×2048, twice the current resolution, which will allow for sharper images and many more possibilities of use.
The natural language compression that this platform introduced with version 5 was a substantial improvement when interacting with this AI, however, and although it is no longer necessary to continue using commas to specify characteristics of an image, this AI takes them into account when generating the results.
With the release of version 6, Midjourney will be able to interpret natural language perfectlyeven though it is informal, so this time, we will finally stop using commas to specify specific characteristics that we want the image we are looking for to have.
Although it seems not to be on the Midjourney roadmap, there are many users who wish they had the opportunity to generate 3D models through a text, a function that will probably arrive in the not too near future, since the first thing is to improve what it already offers to add new functions when the current ones are completely polished.