HI! Welcome back to In technology: artificial intelligencea pop-up newsletter that teaches you about artificial intelligence, how it works and how to use it.
In last week’s newsletter, I shared golden tips for getting the most helpful answers from chatbots like ChatGPT, Bing, and Bard. Now that you’re familiar with the general principle of relationship building with AI, the more specific and detailed instructions you provide, the better results you’ll get, let’s move on to a slightly different realm.
Much of the hype and fear around generative AI has been around text. But there have also been rapid and dramatic developments in systems that can generate images. In many cases, they share a similar structure to text-based generative AI, but they can also be much stranger and lend themselves to highly entertaining creative pursuits.
Image generators are trained on billions of images, which allows them to produce new creations that were once the exclusive domain of painters and other artists. Experts sometimes fail to distinguish between AI-created images and real photographs (a circumstance that has fueled dangerous disinformation campaigns as well as humorous creations). And these tools are already changing the way creative professionals do their work.
Compared to products like ChatGPT, AI tools for image generation are not as developed. They require a few extra jumps and can cost some money. But if you’re interested in learning the basics, there’s no better time to start.
AI Photoshop
Last week, Adobe added a generative AI feature to a beta version of Photoshop, its iconic graphics software, and since then, creators of social networks like TikTok and Instagram have been buzzing about it.
I have some experience with Photoshop. When I tested the new feature, called Generative Fill, I was impressed with how quickly and proficiently the AI performed tasks that I would have spent at least an hour doing on my own. In less than five minutes and with just a few clicks, I was using the feature to remove items, add items, and swap backgrounds.
(To experience these tools for yourself, start by signing up for a free trial of Adobe Creative Suite. Then, install the new Adobe Photoshop beta, which includes the Generative Fill.)
After installing Photoshop beta, import a photo and try these tricks:
-
To change a background, click the object select icon (it has an arrow pointing to a box), then in the Select menu, click inverse to select the background. Then click the Generative Fill box and type a prompt or leave it blank to let Photoshop come up with a new background concept for you.
I used these steps to edit a photo of my corgi, Max. I typed kennel for the prompt and clicked “generate” to replace the background. Here’s the before (left) and after.
The New York Times photo editors do not enhance or alter photos or generate images using artificial intelligence. But my first thought after testing Generative Fill was that photo editors working in other contexts, like marketing, may soon be out of work. When I shared this theory with Adobe’s chief technology officer Ely Greenfield said it could make photo editing more accessible, but was optimistic that humans would still be needed.
I can make really nice pictures with it, but frankly, I still make boring pictures, he said. When I look at the content artists create when you put it in their hands versus what I create, their stuff is so much more interesting because they know how to tell a story.
I confess that what I’ve done with generative fill is far less exciting than what others have been posting on social media. Lorenzo Green, who tweets about artificial intelligence, released a collage of famous album covers, including Michael Jackson’s Thrillers and Adele 21 which have been expanded with a generative fill. The results were quite amusing.
(One note: If installing Photoshop seems daunting, a quicker way to test Adobe’s AI is to visit the Adobe Firefly website. There you can open the Generative Fill Tool, upload an image, and click on the add tool to draw a subject, such as a dog. Then click background and type a message such as beach.)
Multiple image generators
Tools like DALL-E and Midjourney can create completely new images in seconds. They work similar to chatbots: you type a text message, the more specific the better.
To write a quality prompt, start with the medium you want to emulate, followed by the subject and any additional details. For example, typing a photograph of a cat wearing a sweater in a brightly lit room into the DALL-E prompt box will generate something like this:
DALL-E, owned by Open AI, the creator of ChatGPT, was one of the first widely available AI image generators that was simple for people to use. For $15, you get 115 credits; one credit can be used to generate a set of four images.
Midjourney, another popular image generator, is a work in progress, so the user experience isn’t as polished. The service costs $10 a month, and entering requests can be a little trickier, because it requires joining a separate messaging app, Discord. However, the project can create high-quality realistic images.
To use it, join Discord and then request an invitation to the Midjourney server. After joining the server, inside the chat window, type /image followed by a prompt. I typed /imagine a manga cover of a corgi in a ninja turtle suit and it generated a series of convincing images:
While it’s fine to type a basic request, some have found obscure prompts that have generated outstanding results (Beebom, a tech blog, has a list of examples). At Columbia University, Lance Weiler is teaching students how to leverage artificial intelligence, including Midjourney, to produce artwork.
Whichever tool you use, keep in mind that it is up to you to use this technology responsibly. Technologists warn that image generators can increase the spread of deepfakes and disinformation. But the tools can also be used in positive and constructive ways, like enhancing the look of family photos and brainstorming artistic concepts.
What’s next?
Next week, I’ll be sharing some tips on how to use AI to speed up aspects of office work, like writing talking points and generating presentation slides.
In case you were wondering, the delightfully zany image at the top of this newsletter was created by a human illustrator. Charles Desmarais not by artificial intelligence
#edit #generate #stunning #photos
