Although it seems that Artificial Intelligence is something new, actually many years with us, however, it was not until 2022, when a large number of projects began to be announced that make it possible to get the most out of this technology, based on a brief description, automatically generate an image or text. Midjourney, DALL-E, Stable Diffusion, ChatGPT and Bing Chat are the best known Artificial Intelligences, however, they are not the only ones.
Microsoft announced a few days ago the integration of GPT4 in all the applications that are part of Office, an integration that will allow, for example, to generate presentations based on the data of a document, analyze a spreadsheet to summarize the most important points, create a summary of several text documents, automatically generate responses to emails and much more.
How Firefly works
It remained to be known what Adobe‘s plans were to integrate Artificial Intelligence into its applications, plans that have already been revealed, starting with its name: Firefly. Firefly works exactly the same as the other AIs that allow you to generate images based on a description, however, it adds an interesting function not available in these that allows you to set the range of colors that you want to use, the type of lighting and the style of an image. much simpler way than other Artificial Intelligences currently available.
In addition, we can generate images based on others that we have, that is, using them as a base to ask Firefly to add modifications to the image . But, best of all, is that, as we can see in the video of the announcement, all the elements that are generated in the image will be distributed in independent layers, so that we will be able to customize their settings, including the size to adapt it to What we are looking for, in addition to moving it to another location without the proposal by the AI, we do not quite like it.
It also allows us to use several images so that Firefly combines them and shows the best of each one, an option that at the moment is not available in any of the other AIs that allows us to generate images based on others or based solely on a description. Another interesting function that it offers us is the possibility to reduce the grain of the images with low resolution that we want to enlarge. While this is certainly not a new feature, it is appreciated that it is also included in Firefly.
This Adobe AI, they say, has been trained with millions of royalty-free photos available on Adobe Stock, which represents enormous peace of mind for designers who do not want to see their designs accused of using an AI based on copyrighted images. From author.
Try Adobe AI
If we want to try this new AI from Adobe, it is only necessary to have an Adobe account and visit the following link where we must enter the data and sign up for the waiting list . At the moment Firefly is in beta phase and is not integrated into any of Adobe’s applications, an integration that will come to Photoshop, Express, Lightroom in the coming months and that will also be available independently through Adobe Creative Cloud, for what will be necessary to go through the box to be able to use it.
