Using A.I. for Stunning Photo Editing and Generation

Welcome back to On Tech: A.I., a newsletter that explores the world of artificial intelligence and how it can be used. In the last issue, we discussed how to get the most out of chatbots like ChatGPT, Bing, and Bard. This week, we’ll be exploring the exciting world of generative A.I. and how it’s changing the way we create images.

While much of the hype around generative A.I. has been focused on text, there have been significant developments in systems that can generate images. These image generators are trained on billions of images, allowing them to produce new creations that were once the sole domain of painters and other artists. In many cases, experts can’t tell the difference between A.I.-created images and actual photographs.

One of the most exciting developments in this area is Adobe’s new generative A.I. feature in its iconic graphics software, Photoshop. The feature, called “generative fill,” allows users to remove objects, add objects, and swap backgrounds with just a few clicks. While image generating A.I. tools are not as well developed as products like ChatGPT, they are changing the way that creative professionals do their jobs.

To try out generative fill for yourself, start by signing up for a free trial of Adobe Creative Suite and installing the new Adobe Photoshop beta. Once you have Photoshop beta installed, import a photo and try these tricks:

– To change a background, click the “object selection” icon, then under the Select menu, click “inverse” to select the background. Next click the “generative fill” box and type in a prompt — or leave it blank to let Photoshop come up with a new background concept for you.

– To remove objects, use the lasso tool. Trace around the object you want to remove, then click the “generative fill” box and hit “generate” without entering a prompt.

While generative fill is an exciting development, there are other image generators out there that can create entirely new images in seconds. Tools like DALL-E and Midjourney work similarly to chatbots: you type in a text prompt, and the A.I. generates an image based on that prompt.

DALL-E, which is owned by Open AI, was one of the first widely available A.I. 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 is not as polished. The service costs $10 a month, and entering prompts can be a little more complicated, but it can create high-quality, realistic images.

To use Midjourney, join Discord and then request an invitation to the Midjourney server. After joining the server, inside the chat box, type “/imagine” followed by a prompt. While it’s fine to type in a basic request, some have found obscure prompts that generated exceptional results.

Whichever tool you use, bear in mind that the onus is on you to use this tech responsibly. Technologists warn that image generators can increase the spread of deepfakes and misinformation. But the tools can also be used in positive and constructive ways, like making family photos look better and brainstorming artistic concepts.

In conclusion, generative A.I. is changing the way we create images. While image generating A.I. tools are not as well developed as products like ChatGPT, they are becoming more accessible and are already changing the way that creative professionals do their jobs. Whether you’re using generative fill in Photoshop or experimenting with DALL-E or Midjourney, the possibilities are endless. Just remember to use this tech responsibly and have fun!