By now I think everyone has heard about DALL-E, the image synthesis tool that uses the latest artificial intelligence technology to generate images based on text prompts. Here's an excerpt from a recent Washington Post article and an image from an Ars Technica piece.
A DALL-E example of "An astronaut riding a horse." Ars Technica
Since the research lab OpenAI debuted the latest version of DALL-E in April, the AI has dazzled the public, attracting digital artists, graphic designers, early adopters, and anyone in search of online distraction. The ability to create original, sometimes accurate, and occasionally inspired images from any spur-of-the-moment phrase, like a conversational Photoshop, has startled even jaded internet users with how quickly AI has progressed.
Five months later, 1.5 million users are generating 2 million images a day. On Wednesday, OpenAI said it removed its waitlist for DALL-E, giving anyone immediate access.
The introduction of DALL-E has triggered an explosion of text-to-image generators. Google and Meta quickly revealed that they had each been developing similar systems, but said their models weren't ready for the public. Rival start-ups soon went public, including Stable Diffusion and Midjourney, which created the image that sparked controversy in August when it won an art competition at the Colorado State Fair.
Seemingly superficial generations like an
avocado chair showed that OpenAI had built a system that is able to apply the characteristics of an avocado to the form factor and the function of a chair, Murati said.
The avocado-chair image could be key to building AGI that understands the world the same way humans do. Whether the system sees an avocado, hears the word
avocado, or reads the word
avocado, the concept that gets triggered should be exactly the same, she said. Since DALL-E's outputs are in images, OpenAI can view how the system represents concepts.
I couldn't resist the urge to try it out with some numismatic prompts.
Buffalo nickel with the legend "This is not a coin"
I'll give DALL-E a "B" on this one - it at least looks like a coin, has a Buffalo and a legend, just not the legend I wanted.
Pine tree shilling in palm of pilgrim's hand on Thanksgiving
Um, not even close. There are plenty of well-labeled Pine Tree Shilling images on the web. I'll give this a "D".
large rare gold coin on display in museum with people looking in amazement
I'll give this one an "A-". Not bad!
Gort the Robot walking through a coin show
I dunno - a "B" maybe...
Harvey Stack walking through a coin show with a cane
You aren't allowed to use the names of celebrities or politicians. I was wondering if it would actually find an image of the late coin dealer Harvey Stack. Maybe it's dumb luck, but it did get the suit and tie, grey hair and glasses. I'll give this a "B". Love the cane made out of a stack of coins! Very creative. When The E-Sylum starts selling merch, we'll have to stock some of those. Interesting that the cane comes with a top hat.
Wondering what DALL-E thinks The E-Sylum would look like, I tried text from our splash page, http://e-sylum.org/.
history and artistry of coins, medals, tokens or paper money, digital art
Guess we're kinda creepy... Happy Halloween.
To give it a try yourself, see:
Available in Beta
To read the complete articles, see:
DALL-E image generator is now open to everyone
AI can now create any image in seconds, bringing wonder and danger
Bonus robot article - Maillardet's automaton:
This Creepy Robot Just Showed Up at the Franklin Institute One Day
Wayne Homren, Editor
The Numismatic Bibliomania Society is a non-profit organization
promoting numismatic literature. See our web site at coinbooks.org.
To submit items for publication in The E-Sylum, write to the Editor
at this address: email@example.com
To subscribe go to: https://my.binhost.com/lists/listinfo/esylum
Copyright © 1998 - 2021 The Numismatic Bibliomania Society (NBS)
All Rights Reserved.
NBS Home Page
Contact the NBS webmaster