Not knowing how to draw will no longer be an impediment to be able to make graphic reality what you imagine, or at least what can be described in words. All this thanks to Dalle-2, an Artificial Intelligence capable of generate illustrations with high quality graphics starting from descriptions which do not even need to be particularly detailed or concrete.
Dalle 2 will be of great use to people with poor drawing skills
Investor and discloser Javi Lopez has explained in a Twitter thread some of the features and advances of Dalle-2, giving as an example the result obtained after describing something like “an astronaut raccoon with the cosmos reflected in the glass of his diving suit dreams of the stars.”.
Although it may not look like it behind this illustration is not the imagination or talent of an artist but the work and “sensitivity” of an artificial intelligence.
Dalle-2 received only this text: “A raccoon astronaut with the cosmos reflecting on the glass of his helmet dreaming of the stars” and generated this image. Flip pic.twitter.com/oe7iXil4Ct
– Javi Lopez ⛩️ (@javilop) April 8, 2022
It is not yet fully open to the public but from the Dalle-2 website those researchers, developers or people interested in artificial intelligence can request access to the project. Some are already sharing on the Internet the results obtained, such as the illustrator Carmen Lau, who has shared a drawing made by herself and the result obtained by Dalle-2 after describing the same illustration to her with words. Lau herself acknowledges that she likes more the work created by Dalle-2.
I tried using DALL-E to recreate one of my own digital illustrations by inputting a verbal description of it. Left is my original, painted in Photoshop with a Wacom tablet. Right is the generated one. I actually think I like it more, esp. colors! But it does worse on fine details pic.twitter.com/JvbxDwCn9Z
– Carmen Lau (@carmenleelau) April 8, 2022
Lau explains that in his experience Dalle-2 works best if it does not receive extremely long or complex instructions and that it may prove to be of great help to people with little or no artistic or creative abilityas well as to obtain preliminary models of artistic concepts.
For the moment Dalle-2 is still in the early stages of its development and, like other artificial intelligences specialized in specific tasks, there are still years of work, evolution and contributions from various teams before it can perfect its capabilities, but the truth is that so far the examples shown of what Dalle-2 is capable of achieving, remember, based on descriptions of few words, are surprising and some of them really beautiful.
Not only that but, in addition, this artificial intelligence is capable of modifying photographs by introducing changes according to the assigned instructions. In this way it can replace, for example, a dog with a cat in an image. Just as could be easily achieved using Photoshop, but made even simpler: just tell Dalle-2 to “change the dog for a cute cat”.
Dalle-2 today makes it possible to retouch images to the level of changing any element in them.
To the extent of changing a dog for a cat and having it perfectly integrated pic.twitter.com/UTrRfjFZIP
– Javi Lopez ⛩️ (@javilop) April 12, 2022
There are many questions about the results obtained with Dalle-2, even in its still preliminary stagesdalle-2: Are illustrators’ jobs in danger, and can anyone become an “illustrator” by dictating the right instructions to Dalle-2?
will we be able to believe our eyes in front of a photograph? Will this type of artificial intelligences be integrated into the mobiles themselves to modify/retouch photographs by voice instructions? What about intellectual property rights? Is Dalle-2 the “creator” of these illustrations or just a tool and the merit belongs to the one who dictates the description of what the image should contain?
will artificial intelligence eventually replace artistic creation? Are there already some capable of creating poses imitating the great authors? Will androids dream of electric sheep?