With the proliferation of artificial intelligence models in recent months, companies have started to invest in them and release their own artificial intelligence models one by one. Among them is the most notable company of recent days Adobe it happened.

Firefly, Adobe’s new artificial intelligence model being tested, is still in development. ambitious enough to challenge many visual artificial intelligence models. However, it can also fail in many areas.

It fails to model people while producing much higher quality and sharper images.

Unlike other artificial intelligence models from Adobe, such as neural filter and smart object selection, Firefly lets you create images from scratch instead of manipulating them. Firefly works in a similar way to its competitors such as DALL-E and Midjourney in terms of use and can provide users with much higher quality and sharper images. Although artificial intelligence, which is still in the early testing phase, creates very detailed and successful scenes in some images in some cases can create absurd or overly simple images.

The majority of users who tested Firefly stated that the system was successful in creating animals and environments; it proves to fail almost every time the system is asked to paint people. The main reason for this is that this artificial intelligence tool takes advantage of Adobe’s own stock image pool. Although there are mainly landscape and animal images in the pool, It is stated that the images with people are very few.

Firefly also focuses on protecting the rights of working people

One of the most criticized aspects of DALL-E and Midjourney is that these artificial intelligence models self-develop by scanning visual sites, social media, and portfolios on the Internet, especially Shutterstock. Of course, this means that the images of the people who make the art they are sharing on the internet. It causes unauthorized use and similar images can be created using artificial intelligence systems..

Adobe, on the other hand, explains that it has taken several measures to prevent a similar problem with Firefly. For example; As we just mentioned, Firefly only trains itself with royalty-free images in Adobe’s image repository. In this way, the content of content producers who share their work on the Internet is not used without permission.

In addition, in the metadata and codes of all images created with Firefly It is clearly stated that the image was created by the artificial intelligence system. In this way, people can easily distinguish between images created by artificial intelligence and those drawn by hand.

Adobe also states that design companies can customize and develop Firefly using their own portfolios. Since the improvements made only apply to companies, Copyrighted images of companies can also be protected.

It is unknown when Firefly, which is still in beta, will be available to all users, but if you want to sign up for the beta located here You can use the link.