Artist Recreates The Simpsons Characters Realistically Using AI, And The Results Look Cursed (30 Pics)

"The Simpsons has been around all my life," Jaram told Bored Panda. "From the first Christmas episode; we all would huddle around before Christmas and watch it."

According to creator Matt Groening, the show adopted the concept of a large supporting cast from the Canadian sketch comedy show Second City Television.

Jaram said he really appreciates the cast. "Character design is Groenig all the way, that's his thing. Good for him."

"The idea for this series came to me from trying to be creative with AI, pushing its limits and seeing what it could do," Jaram explained.

"But if you go to my website, you'll see some non-AI stuff (traditional art) that also went viral, for example, mixing up things like Muppets as real people."

"TikTok has just been a venue to share the ideas I've gotten from AI."

Artificial intelligence art has been booming really hard lately. Especially after an art prize at the Colorado State Fair was awarded to a work that – unbeknown to the judges – was generated by one of its systems.

But social media has also seen an explosion of weird AI images from text descriptions, such as "the face of a Shiba Inu blended into the side of a loaf of bread on a kitchen bench, digital art."

Or "a sea otter in the style of 'Girl with a Pearl Earring' by Johannes Vermeer."

According to Ph.D. student Rodolfo Ocampo who specializes in human-AI creative collaboration, you could say this revolution began in June 2020, when a company called OpenAI achieved a big breakthrough in the field with the creation of GPT-3, a system that can process and generate language in much more complex ways than earlier efforts.

You can have conversations with it about any topic, ask it to write a research article or a fictional story, summarize text, craft a joke, and do almost any imaginable language task there is.

"In 2021, some of GPT-3's developers turned their hand to images," Ocampo said. "They trained a model on billions of pairs of images and text descriptions, then used it to generate new images from new descriptions. They called this system DALL-E, and in July 2022 they released a much-improved new version, DALL-E 2."

"Like GPT-3, DALL-E 2 was a major breakthrough. It can generate highly detailed images from free-form text inputs, including information about style and other abstract concepts."

Soon after the introduction of DALL-E 2, a few competitors emerged. One is the free-to-use but lower-quality DALL-E Mini (developed independently and now renamed Craiyon), which was a popular source of meme content.

Around the same time, a smaller company called Midjourney released a model that matched DALL-E 2's capabilities way better. "Though still a little less capable than DALL-E 2, Midjourney has lent itself to interesting artistic explorations." Ocampo pointed out. "It was with Midjourney that Jason Allen generated the artwork that won the Colorado State Art Fair competition."

But does it mean that anyone can generate vivid visual content, image or video, with a few lines of text and a click of a button? Looking forward, what will it mean when social media algorithms not only curate content for your feed but generate it?

"Some speculate that, in the short term, this means human creativity and art are deeply threatened," Ocampo said.

"Perhaps in a world where anyone can generate any images, graphic designers as we know them today will be redundant. However, history shows human creativity always finds a way. The electronic synthesizer did not kill music, and photography did not kill painting. Instead, they catalyzed new art forms."