The internet was already a weird place, but it suddenly got even weirder thanks to the explosion of weird AI art created by imagers like DALL E 2, MidJourney, and Craiyon. From weird cartoon crossovers to surreal food to apocalyptic selfies, DALL E 2 and others with varying degrees of success really do seem capable of creating any weird AI art you can describe in their dialogs.
Of course, DALL·E 2 and other AI art generators don’t think of these things themselves. They execute the written notice given to them through the millions of images and captions they have received. So the results are as bizarre as users’ imaginations. There are a lot of existential concerns about where this is all going and what it means for artists, but AI isn’t going to take over the world and enslave us just yet. We wait.
OpenAI, the makers of DALL·E 2, recently announced pricing and will expand access to the platform over the next month, but for now there is still a waiting list. Do you want to know how to make it work for you? See our guide to how to use DALL E 2. In the meantime, here are some of the strangest pieces of AI art created by DALL·E 2 and other AI platforms so far.
The last selfie ever taken
@elalgotrippy (opens in a new tab)
♬ The Just Wrath of an Honorable Man – Colin Stetson (opens in a new tab)
One of the latest trends making the rounds on TikTok is the use of AI art generators to create “the last selfie ever taken.” Started by Tiktokker @robotoverloards (opens in a new tab) and taken by others, the results appear suitably apocalyptic showing androids and skeletons posing for photographs amid desolate scenes of a burning planet. The most worrying thing is that selfies seem to continue to exist in recent days. It’s unclear which AI art generator they used to create the images; it appears that the original series may have been created using MidJourney. An even deeper conspiracy theory is also brewing: what is the blue cube that appears in several images?
Ronald McDonald in Star Trek
A still from Ronald McDonald in an episode of Star Trek: The Next Generation (1987) #dalle2 pic.twitter.com/UhTzAwCPHlJuly 31, 2022
On a lighter note, much of the weirder AI art created in DALL E 2 has involved putting characters and famous people in unlikely places. And it seems that the only limit is your imagination.
‘Average’ people in ‘average’ cities
Average French people in average French cities. The architecture looks a lot like what I think it should be. Lots of flowers too. Clothes with style. I see the guy in number 1 smoking Gauloises cigarettes. #dalle2 pic.twitter.com/cDh5bmZlBmAugust 2, 2022
So let’s remember what people look like today, before the apocalypse and before we sent fast food restaurant mascots into deep space. Just average people in average cities. there are kranen (opens in a new tab) on Twitter did exactly that by asking to show average people in average cities in various countries. But hmm, they also look a bit strange.
Spongebob Squarepants Godzilla
#dalle2 This is it. This is the best message I will ever come up with. pic.twitter.com/GoxvSIrwW4July 23, 2022
Perhaps Ai should stick to the fantasy then. Of all the DALL E 2 cartoon mashups (and there are many), this has to be our favorite. It is improved by giving specific instructions to the artist, not just the combination of two characters.
A Rubik’s Cube Peanut Butter Sandwich
data scientist Max Woolf (opens in a new tab) has been testing how reliably DALL·E 2 can follow instructions when asked to produce photos of food and to see if it could produce new ideas for food content on the Internet. For example, to make a peanut butter sandwich in the shape of a Rubik’s cube. Yes, I could.
Animals live their dreams…
A raccoon playing tennis at Wimbledon in the 1990s #dalle2 #dalle pic.twitter.com/45tBFKJ9ZJMay 14, 2022
There is a whole category of AI images dedicated to anthropomorphism, showing playing sports, presenting the news and much more.
…and fight He-Who-Must-Not-Be-Named
Expect every brand marketing team and their dog to try to plot a campaign around AI art generators in the coming months. That could tire very quickly, but some sharp marks have been very quick. Heinz he was quick out of the exit gates, and so was dogsplanet.com (opens in a new tab).
The website for dog lovers has used Discord-based MidJourney to create all sorts of canine creations with some hilarious results, the highlight being the epic fight between a cocker spaniel and Voldemort. If Harry Potter were a dog, he would be a cocker spaniel, they believe, and based on this we would have to agree.
the apple car
AI art generators have opened up new possibilities for fans of products rumored to be in production but whose creators don’t want to show us yet. We wanted to get a peak at the rumored apple car since we found out about the project. The designer and youtuber Juan Mauriello (opens in a new tab) I thought that DALL·E 2 could imagine what it will look like. Of course, typing ‘Apple Car’ resulted in a car that looked like a fruit, so he chose “Minimalist sports car inspired by a MacBook and a Magic Mouse, built with aluminum and glass.”
Duolingo Tracking Camera
We finally get to see what everyone’s favorite polyglot owl is up to in his sleep thanks to Duolingo’s tracking camera. This was actually created at Craiyon, formerly called DALL-E mini, until the creators of DALL-E had words.
greener cities
Not everything is apocalypse and anthropomorphism in the art of AI. Some people are really putting it to productive use. Yes, really, and good for them. Artist Zach Katz is using DALL·E 2 to show what city streets would look like without cars and with additional greenery and water features. He is much more sensible and suggests that AI could have a use in urban planning. Your Twitter account @betterstreetsai (opens in a new tab) has gained thousands of followers in just weeks, and has a backlog of placement requests to test.
‘Pug-a-choo’
Enough of such sensible and valuable activities. Why use AI to create something useful when you could create a cross between a Pokémon and a dog?
R2D2 being baptized
There seem to be a lot of Star Wars fans using DALL E 2 and the like, and some of the weirder AI art pieces involve characters being placed in unlikely situations, from Jar Jar Binks on Love Island to an MRI of Darth Vader, and yes R2DR after finding God. This is another one created on Craiyon.
Nike Air Sushi being harassed by a bear
Got approval for Dall-e 2 today! #dalle #dalle2 “a pair of Nike AF1s made from salmon sashimi, a hungry bear approaches in the distance, award winning product photo” pic.twitter.com/L1QrCjKsyFAugust 1, 2022
We’ve seen character mashups, artist mashups, what about the clothes? In fact, given some of the footwear collaborations we’ve seen in recent years, we wouldn’t be surprised if they saw the light of day. And look how much the bear loves them.
The Muppets crash London Fashion Week
⌨ “London Fashion Week’s most ridiculous looks modeled by the cast of muppets, lfw”💅#lfw #AI-generated fashion with #dalle2 🤖 #dalle 🎨 #aiart pic.twitter.com/Slu25GPTGUJune 6, 2022
And speaking of fashion, we love these runway looks modeled by some of Jim Henson’s best as played by DALL E 2. The weirdest AI-art fashion collection we’ve seen yet.
A man kissing a blue deer.
Bwahaha!!! THIS IS SO STRANGE!!! 😳😱🤣💀 So, for this round in Dall-E 2, I wanted to generate an image of a man kissing a blue deer (which was supposed to be anthro, like Bam) in an enchanted forest, painted in a romantic period style . (think late 1700s-mid 1800s). Dying of laughter! pic.twitter.com/d2Ygwzn5OrJuly 31, 2022
If you’re using an AI art generator like DALL·E 2, you’ll soon learn that you have to be very specific with your prompts. This Twitter user seems to have intended to create an image of a man pranking Bam from Animal Crossing, but instead asked for a man kissing a blue deer instead. So what they got was, well, a man kissing a blue deer.
Borat as Dr Strange
some dall-e 2 results pic.twitter.com/6r28Te1ksLAugust 2, 2022
AI art generators could be an interesting aid for casting directors. Wondering if a certain actor could fit a role? Borat as Dr. Strange, for example? Ask DALL E 2.
Is the art of AI really art?
The big question is, but is it art? Some argue that AI-generated art is not really art because it is created by a machine and therefore lacks intrinsic psychic meaning to the agent. In reality, the AI ​​is not creating art, but rather replicating the art from the database it is fed, but in new combinations and forms. AI is not based on personal or collective experiences like an artist does.
That said, the AI ​​art generator is acting on human instructions. So while the AI ​​generator itself can’t be described as an artist, the human writing the ad perhaps could (which might explain why people become so protective of the ads they used to create an image). In this sense, the AI ​​art generator would simply be an artistic tool more like a brush or a pencil.
As for the commercial aspect of art, human creators of AI-generated pieces can sell their work, depending on the platform they use. There is some legal debate about whether images created by AI can be copyrighted, but OpenAI has recently announced that DALL E 2 can now be used to do commercial work, meaning that the human instructing the machine can sell the resulting job.
We have already seen some people do this, selling their work as NFTs. And Christies sold an AI-generated artwork, “Edmond de Belamy, de La Famille de Belamy,” by the French art collective Obvious, as early as 2018.
Can you tell if a work of art was made by AI?
First it was deepfakes, now it’s AI art generators. It is becoming more and more difficult to know if something is real or fake, and if something was created by a human or a machine. With the images created by some of the free AI art generators, it’s pretty obvious because they tend to contain glitches, blurs, and weird effects that no human artist would create (unless they were intentionally trying to replicate the look of an AI art generator). , now it’s getting complicated!).
Some of the more advanced recent releases like DALL·E 2 can be more difficult to pin down. Yes, many images still have an uncanny valley look to them, but much of the platform’s output could pass for human-created illustrations or photography. It may be that the only giveaway is when the artist has left the AI ​​art generator signature; in the case of DALL·E 2, this is a row of colored squares in the bottom right of the image.
Read more: