Dall-E Mini: Everything to know about Strange AI Art Creator

On the internet, nightmare fuel is common place. The latest source: Dall-E Mini, an artificial intelligence tool that catches the attention of social media thanks to the weird, funny and occasionally disturbing images it creates from text prompts.

AI-generated images showing Batman surfing.

Batman surfer.

Erin Carson / Dall-E Mini

Dall-E Mini lets you write a short sentence describing an image, one that theoretically only exists in the deep depressions of your soul, and within a few seconds the algorithm will manifest this image on your screen.

Odds are you’ve seen some Dall-E Mini pics pop up in your social media feeds while people are thinking about the wildest calls they can – maybe it’s Jon Hamm eating ham or Yoda robbing one grocery store.

This is not the first time that art and artificial intelligence have caught the attention of the internet. There is a certain appeal to seeing how an algorithm tackles something as subjective as art. In 2016, for example, actor Thomas Middleditch made a short film based on a script written by an algorithm. Google has produced more than a few tools that link art and artificial intelligence. In 2018, its Arts & Culture app let users find their doubles in famous paintings. Or Google’s AutoDraw will find out what you are trying to doodle and fix it for you.

There are other text-to-image systems, such as OpenAI’s Dall-E 2 and Google Image, that are not yet available to the masses.

Here’s what you need to know about the Dall-E Mini and its AI-generated art.

What is the Dall-E Mini?

The Dall-E Mini is an AI model that creates images based on the prompts you give it. In an interview with publication I, programmer Boris Dayma said that he originally built the program in July 2021 as part of a competition hosted by Google and an AI community called Hugging Face. Dayma did not immediately respond to a request for comment.

How does it work?

Anyone can enter a prompt and press the “run” button (although you will probably get an error message about traffic to the tool and will have to try again). The Dall-E Mini will spit out its results in the form of a 3×3 grid containing 9 images. A note about the tool on its website says that it was trained in “unfiltered data from the Internet.”

How good is AI?

Not surprisingly, the Dall-E Mini is a small hit or miss. In the interview with I News, Dayma said that AI is better with abstract painting, less with faces. A landscape of a desert is quite beautiful. A pencil sketch by Dolly Parton seems to be able to steal your soul. That Paul McCartney eats kale will take years from your life.

A cat made of mostly pink laser light.

Here is a cat made of lasers.

Erin Carson / Dall-E Mini

Dayma said, however, that the model trains (that the ability to learn is one of the things people love – and fear – about AI), which means it can be improved over time. And with the viral popularity of the Dall-E Mini, the point is to fall over the most bizarre image you can think of, not necessarily to get a perfect impressionistic rendition of a waffle house. The fun is more about dreaming up the most bizarre images that do not exist – which perhaps should not exist – and bringing them into a damned existence.

Dall-E also has a note that says image generation could have a less fun side and could be used to “amplify or exacerbate societal imbalances.”

Is the Dall-E Mini related to the Dall-E 2?

No, they are not connected. Dall-E 2 is also a tool for generating AI images that was launched as a research project this year. It was created by AI research and implementation firm OpenAI and is not widely available.

What kind of images do people create?

On social media, you can find an abundance of weird Dall-E Mini creations, from Thanos in a Walmart looking for his mother, to Jar Jar Binks winning the Great British Bake Off. Here are some other highlights.

Leave a Comment

Your email address will not be published.