Original Source Here
Everything You Need to Know About Dall-E Mini, the Odd AI Artist
Do you want to know what your favorite character looks like while he’s surfing? Dall-E Mini can assist you.
The team over at OpenAI have recently created a powerful piece of software, able to produce a wide range of images in seconds, just from a string of words it is given. The most recent source is Dall-E Mini, an AI tool that has gained traction on social media for the strange, amusing, and occasionally unsettling visuals it generates from text prompts.
Dall-E Mini allows you to input a short sentence describing an image, one that supposedly resides only in the depths of your soul, and the algorithm will manifest that image onto your screen in a matter of seconds.
You’ve probably seen some Dall-E Mini photos in your social media feeds as people come up with the most bizarre instructions they can think of, such as Jon Hamm eating ham or Yoda stealing a convenience store.
This isn’t the first time art and artificial intelligence have gotten people’s attention on the internet. It’s intriguing to watch how an algorithm approaches something as subjective as art. Actor Thomas Middleditch, for example, made a short film in 2016 based on a story written by an algorithm.
Google has created a number of tools that combine art with AI. Its Arts & Culture app, which launched in 2018, allowed users to find their doppelgängers in famous artworks. Alternatively, Google’s AutoDraw can figure out what you’re trying to doodle and correct it for you.
There are other text-to-image systems, like OpenAI’s Dall-E 2 and Google Imagen, that aren’t yet available to the masses.
What is Dall-E Mini
Dall-E Mini is an AI model that generates graphics in response to your commands. Boris Dayma, a programmer, told the journal I that he first created the program in July 2021 as part of a competition sponsored by Google and the Hugging Face AI group. A request for comment from Dayma was not immediately returned.
How does it work
Anyone can write in a prompt and push the “run” button (albeit you’ll probably get an error warning about tool traffic and have to try again). The results of Dall-E Mini will be presented in the form of a 3×3 grid including 9 photos. The program was trained on “unfiltered material from the internet,” according to a disclaimer on the company’s website.
How good is the AI
The Dall-E Mini is hit or miss. Dayma claimed in an interview with I News that the AI is excellent at abstract painting, but not so much with faces. A desert scene is incredibly lovely. A pencil doodle of Dolly Parton appears to have the potential to steal your soul. If you eat kale like Paul McCartney, you’ll live longer.
With Dall-E Mini’s viral success, the goal is to come up with the most odd image you can conceive of, rather than a beautiful impressionist portrayal of a Waffle House. The thrill is in conjuring up the most bizarre pictures that don’t exist or perhaps shouldn’t exist, and then bringing them to life.
Dall-E also has a note saying that image generation could have a less fun side and could be used to “reinforce or exacerbate societal biases.”
Is Dall-E Mini related to Dall-E 2
They aren’t linked in any way. Dall-E 2, a tool for creating AI images that was launched as a research project this year, is also a tool for generating AI images. It was developed by OpenAI, a business that specializes in AI research and deployment, and it is not widely available.
To get access to unlimited stories, you can also consider signing up to become a Medium member for just $5. If you sign up using my link, I’ll receive a small commission (at no extra cost to you). Or you connect with on LinkedIn.
Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot