Have you ever wondered what Homer Simpson would look like if painted by Vincent van Gogh? What about Batman riding a skateboard?
Well, you don’t have to wonder much longer. A hugely popular artificial intelligence art generator has taken the internet by storm, turning curious users’ most outlandish thoughts into reality.
Dall-E mini software is a free, open-source AI that produces images using text prompts.
Users just need to enter a simple description and hit ‘run’. Let’s use “Batman riding skateboard” as an example.
In seconds, the program can interpret the description and spit out nine images matching the request.
And voilà, watch Bruce Wayne transform into Tony Hawk before your eyes. Here are some of the creations the news guide has put together before.
Dall-E Mini brings all kinds of crazy and wonderful ideas to life. Homer by Van Gogh: The Simpsons patriarch has never looked so good.
How does it work?
Named after Spanish artist Salvador Dali and Disney Pixar robot Wall-E, Dall-E Mini is the brainchild of Houston-based programmer Boris Dayma.
The model started making waves online in the past two weeks, but Mr. Dayma built the program in July 2021 as part of a Google AI competition.
He says Dall-E Mini takes 400 to 500 million pieces of “unfiltered data from the Internet” and puts them together to fulfill users’ requests.
Speaking to The I, Mr. Dayma said the driving idea behind its creation was to make AI accessible to everyday people.
“It was both a technical challenge and an interest in having something publicly available.”
The model even gave Prime Minister Anthony Albanese a Warhol-esque makeover. In this creation, Dall-E mini imagines opposition leader Peter Dutton holding a koala bear.
Work in progress
The program can be a bit disappointing – which Mr. Dayma openly admits.
Dayma says the app sometimes struggles with more precise details, such as faces.
“The hardest thing is definitely the people,” he said. “When you draw a landscape with Dall-E, it’s great because if nobody notices e’s a small problem with a tree, nobody’s landscape still looks great.
“But if tha face has a problem, notice it. If there is a little flaw with one eye, we can see it. With an avocado, even if it has flaws, it’s good enough.”
Pop singer Taylor Swift is vaguely recognizable by her red lips and blonde locks. Dall-E Mini was able to accommodate this particular request – location and all.
But it’s all part of the process. Like most artificial intelligence, Mr. Dayma says Dall-E mini learns as it goes.
“The model is still in training. It’s still going to improve. Day after day, it only improves a little bit, but u really notice it week after week.” week after week
Where in the beginning, he worked painstakingly to train the model, now it introduces blind – learning as it generates countless images based on the requests of its users.
This tweet perfectly illustrates the evolution of AI’s capabilities. Mr. Dayma has documented the program’s lessons over time. Using the prompt ‘A Pikachu armchair’ as an example, we can see how far Dall-E mini has come in just a few days.
As seen in the top row, the interpretation of the model is incredibly ambiguous. But as time passes, merging the two concepts is much better.
Tweet from @borisdayma
Some highlights
Dall-E’s bizarre mini-creations have spread like wildfire online, some with hundreds of thousands of likes each. Here are some of our favorites so far.
Want to make your own Dall-E mini-creation? Click here.
Tweet from @weirddalle Tweet from @weirddalle Tweet from @iknowmyluck Tweet from @weirddalle Tweet from @weirddalle
More AI news: