In my work related to visual and creative areas, I sometimes like to appreciate errors. Same when generating images using AI. I was in love when I realized that AI at first didn’t fully distinguish clothing, and used it randomly.
In the first images of Mexican fighters I generated, many of them appeared with some fancy women clothing on, some even wore high heels. In case of the family photos, the funny thing was that some of parents’ faces were strangely similar to each other, and that the configuration was also quite random: 2 fathers, 3 mothers with one father (or uncle;) AI could add up to 3-4 wives, and basically came up with any combination that you can imagine. It would not judge you for willing to generate Jesus on plush pink cross, but forbid you from using the word “sucking”. Curious how, and in which way, with growing public use, the new rules and restrictions will block the freedom and diversity of the algorithm.
Sadly, in the new versions of algorithm and its learnings, this freedom is slowly fading as it learns the ”correct use” of certain concepts, also due to a lack of imagination of its users. As always, the masses have a rather ”basic” taste, and it shows through the algorithm also obviously heading in that direction.
Especially because of that, I like to use older versions of the algorithms. I appreciate the unexpected. Mix of people, body features, and aesthetics. I like the unintended sense of humor that algorithm has in this area. What’s most interesting is how every version of the algorithm is different, and can create different outcomes.
As always, if you’re looking for more content, follow me on instagram @igormarcelxd or contact me via www.igormarcel.com
