Midjourney v5 is the latest language model of the popular text-to-image generator known for its realistic creations.
update rolled out Several users on Midjourney’s paid subscriber base and including graphic designer Julie Weiland are sharing their new AI-generated artwork on Wednesday. AI details that the v5 language model brings with it include improved “efficiency, consistency and quality,” Midjourney said on its website.
Many users have especially noted an upgrade in the detail of the human hand, with subjects more likely to have five fingers per hand. In previous models, human hands were often generated with the wrong number of digits, anywhere between four and seven and ten. Those able to test Midjourney v5 have been impressed with the visual upgrades.
“The latest midjourney V5 model is both heavy/scary and attractive,” Weiland told Petapixel.
“Its ability to recreate complex details and textures, such as realistic skin textures/facial features and lighting, is unparalleled,” she said.
While Midjourney is a somewhat unique language model, it works in a similar way to other text-to-image generators such as Stable Diffusion and DAL-E, using worded prompt descriptors to generate images according to the model, Which is trained using human. According to ArsTechnica, the art created as a reference.
There is debate about whether AI-generated art is legal or ethical; However, many Midjourney v5 users believe that with continued upgrades it can become indistinguishable from real art and photography. Wieland believes that AI image generators like Midjourney are likely to be photographers’ companions rather than replacements.
However, the Midjourney v5 is not without its ups and downs. AI image maker Nick St. Pierre shared many of his tasks, for which he used the same prompts as in the previous Midjourney V4 and Midjourney V5. One image was a striking shot of young women in 1960s street style that resembles an outdoor fashion shoot. Upon closer inspection, you can see the floating hands not attached to the body and misshapen faces in the background.
With their latest v5 model, Midjourney founder David Holz on the brand’s Discord recommends that users move away from shorter prompts in favor of “longer, more clear text” to get better results.
Editors’ Recommendations