Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description

By Alma Fabiani

Published Apr 14, 2022 at 11:58 AM

Reading time: 2 minutes

AI research laboratory OpenAI is currently making headlines again for its latest invention DALL·E 2—or should we say, for its update to the success that was its predecessor, DALL·E. To put it simply, DALL·E 2 is a machine learning model that can generate stunning images from text descriptions in less time than ever before.

As many of you probably know, AI systems being able to create images and art from text is nothing new. We’ve previously seen how the technology could help transform your favourite celebrities into Disney characters or even how it could reimagine your childhood cartoon characters as humans. But DALL·E 2, when compared to other machine learning models out there, can generate more realistic and accurate images with four times greater resolution thanks to OpenAI’s advanced deep learning techniques. Not to mention the images are scarily realistic.

@karenxcheng

A demo of DALL-E 2 🤯 will be doing a live demo and taking audience requests, see my IG for details #dalle2 #openai #artificialintelligence

♬ original sound - Karen X

Announced on 6 April 2022 on the company’s Twitter account, the reveal of DALL·E 2 was accompanied by a thread of wonderful photos which quickly grabbed the attention of the platform’s users.

A short video that successfully harnessed the power of the technology—just letting you know, you’re about to see a Panda bear ice skating and a Koala bear dunk a basketball—and what it can do followed the thread:

Like every milestone OpenAI announcement, DALL·E 2 comes with a detailed paper as well as a unique landing page for enthusiasts to read more about how the machine learning model works. A video providing more of an overview of what the technology is capable of doing and what its limitations are has also been shared online.

If you’re not sure you’re up for reading the full paper on DALL·E 2, we’ve got you covered. To put it as simply as possible, the system is a generative model, which is a special branch of machine learning, that creates complex output instead of performing prediction or classification tasks on input data. Basically, you provide DALL·E 2 with a text description and it generates an image that fits the description.

Generative models are a hot area of research that received much attention with the introduction of generative adversarial networks (GAN) in 2014. You probably remember websites such as ThisPersonDoesNotExist or ThisStartUpDoesNotExist, right? Well, these were early examples of what GANs could help us do.

Since then, however, the field has seen tremendous improvements, and generative models have been used for a vast variety of tasks including creating artificial faces, deepfakes, synthesised voices, and more. What sets DALL·E 2 apart from other generative models is its capability to maintain semantic consistency in the images it creates. This consistency is clearly shown in OpenAI’s shared examples.

Let’s say you enter the description “Teddy bears shopping for groceries in the style of ukiyo-e” into the AI system. DALL·E 2 will offer you those images (among many others).

Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description
Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description
Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description

Now, imagine that you changed the description you’ve given it slightly to “Teddy bears shopping for groceries in ancient Egypt,” because why not? In only a few seconds, DALL·E 2 would give you some of these instead:

Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description
Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description
Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description

But what if you wanted those cute bears to be shown shopping again, only using a one-line drawing style instead?

Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description
Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description
Koala bears dunking basketballs? Meet the new AI tech creating realistic images from any description

The point is, the model remains consistent in the examples it offers you depending on the text prompt you give it. This same consistency shows itself in most examples OpenAI has shared so far. Furthermore, DALL·E 2 seems to understand depth and dimensionality, a great challenge for algorithms that process 2D images.

Even if the examples currently shown on OpenAI’s website were cherry-picked, they are still impressive. In fact, to prove how good the technology is, OpenAI’s CEO Sam Altman took to Twitter and asked users to suggest prompts to feed to the generative model. The results (see the thread below) are fascinating.

All that said, it remains to be seen how deep DALL·E 2’s commonsense and semantic stability goes, and how its successors will deal with more complex concepts such as compositionality. In the meantime, though OpenAI’s website invites enthusiasts to get on their waitlist for DALL·E access, in a blog post, Altman suggested a possible product launch as soon as this summer. So start prepping your written descriptions for an AI girl summer.

Keep On Reading

By Charlie Sawyer

Explaining Swiftonomics: Why NFL stans need to be thanking Taylor Swift big time

By Alma Fabiani

This Texas zoo lets you name a cockroach after your ex and have it fed to an animal

By Abby Amoakuh

Celebrity podcaster Bobbi Althoff comes forward as deepfake porn video of her goes viral

By Fatou Ferraro Mboup

Is Kylie Jenner broke? New conspiracy theory suggests the billionaire might be out of cash

By Abby Amoakuh

What is livestream shopping and why do people (wrongly) think the trend is over before it even started?

By Charlie Sawyer

What is the husband stitch? Understanding the controversial procedure laced with medical sexism

By Abby Amoakuh

Zendaya explains how she sneaked in a Spider-Man reference in Challengers

By Abby Amoakuh

Remote Amazonian tribe reports aggressive sexual behaviour in young men after being exposed to internet

By Abby Amoakuh

Drake calls for release of Tory Lanez, proving once more that he’s a rapper for the manosphere

By Abby Amoakuh

Challengers representatives step in after movie poster with racial slur goes viral

By Emma O'Regan-Reidy

Stanley vs YETI: Which tumbler is worth the hype?

By Abby Amoakuh

Influencers are pranking their loved ones by claiming ExxonMobil has invited them on an oil rig brand trip

By Charlie Sawyer

Delulu: The Gen Z slang term for delusional explained

By Abby Amoakuh

Barron Trump is being groomed to take over the Trump empire and the graduation fuss proves it

By Charlie Sawyer

How much are the Love Island All Stars contestants getting paid?

By Alma Fabiani

Watch Dan Schneider’s 19-minute video response to Quiet on Set: The Dark Side of Kids accusations

By Fatou Ferraro Mboup

Forget about bed bugs, a Scabies outbreak is already sweeping the UK

By Abby Amoakuh

Kanye West announces launch of Yeezy Porn, an adult entertainment business

By Abby Amoakuh

Bride walks out on her own wedding after the groom smashed a cake in her face, and she’s not the first one!

By Fatou Ferraro Mboup

Female students fear harassment after all-male committee form pro-life society in Manchester