Skip to main content

5 amazing AI features in Photoshop you can use now

Photoshop is one of the most versatile and powerful photo and image editing tools available, and Adobe is adding amazing new AI features to make it even better.

AI is also coming to Illustrator and Adobe Express. I took a look at how Adobe is expanding possibilities with AI and the results are impressive and easy.

Recommended Videos

AI image generation

A screenshot of Photoshop's AI image generation capabilities.
Photoshop beta has AI image generation capabilities. Digital Trends

You’ve probably seen Photoshop’s Generative Fill feature demonstrated, but it doesn’t just make images bigger. You’ll never have to worry about starting with a blank canvas if you use Photoshop Beta’s image generation feature. Create a blank document, hit Control+A to select all, then type a few words in the Generative Fill text box.

I asked for a “a beautiful landscape photo with a tree beside a huge boulder.” Adobe’s cloud processing quickly returned three options, all nice representations. 

Adding AI-generated objects

A screenshot of adding objects with Photoshop's AI.
You can add objects with Photoshop’s AI. Alan Truly / Digital Trends

You can add objects to an existing photo or image using the same method. Just select a portion of a picture with the lasso or any of the marquee tools, then type in a prompt and click Generate.

It’s similar to the AI image generation mentioned above, but Adobe’s generative fill adds or updates details that fit within the scene instead of creating on a blank canvas. 

I added a nicely glowing UFO behind the tree and rock shown in the first example. That means you don’t have to worry about creating a perfect prompt that includes every element you envision.

Reframing and extending

Before and after screenshots showing how Photoshop's AI can expand the canvas.
Before and after screenshots showing how Photoshop’s AI can expand the canvas. Adobe

When working with photographs, you can add a little (or a lot) to the edge of a picture to reframe it or change the aspect ratio. Once again, generative fill comes to the rescue.

It’s similar to Photoshop’s Content Aware Fill but uses more advanced AI to fill in critical details in a way that blends nicely with the scene.

I used my wife’s photo of my epic icicle sword in this example and extended the top, left, and bottom edges with Adobe’s AI feature.

Expand the canvas with the crop tool, then select the blank edges. It’s important to overlap the photo or image enough that the AI can understand which elements in the background to match.

Removing objects

Before and after screenshots showing how Photoshop's AI Remove tool.
Before and after screenshots showing how Photoshop’s AI Remove tool. Image used with permission by copyright holder

Photoshop’s new AI tools aren’t just for adding new content. You can also remove objects. It’s like Google’s Magic Eraser, but it works on high-resolution images on your desktop computer.

To find Adobe’s AI-powered Remove tool click and hold the Spot Healing Brush tool. A menu will appear, and the remove option is the second in the list.

I brought in a photo of my beautiful wife in the woods. She purposely took a photo with a branch in the foreground, but it serves as a good test of Photoshop’s object removal feature.

After painting over the branch in multiple strokes, Tracey’s chin and red hoody are cleared of branches with minimal distortion that’s easily touched up.

Background swapping

Before and after screenshots showing Photoshop's AI background swapping skills.
Before and after screenshots showing Photoshop’s AI background swapping skills. Image used with permission by copyright holder

It’s simple enough to remove backgrounds in Photoshop. But now, you can try different backgrounds in seconds with Photoshop’s new AI tools. First, select the people and any foreground elements you want to keep. Then invert the selection so you can fill the rest of the picture with new content.

In this example, my jaunty hat made me think of Robin Hood, so I went for a medieval sunrise. I started with the Object Selection tool, then corrected a few errors with the Lasso.

After typing “A beautiful vista of a medieval landscape at sunrise” as the prompt, I was rewarded with a convincing composite. A little adjustment to the color balance made us look right at home in the generated scene.

About Adobe Firefly

Photoshop’s AI image generation uses Adobe Firefly, which is trained on images from Adobe Stock, not public images. That means using Adobe’s AI output in commercial work is safer. Adobe’s generative AI includes “nutrition labels” in accordance with the Content Authenticity Initiative (CAI). That said, it’s also important to note that Adobe states, “Generative Fill is currently not available for commercial use.”

You can use Adobe Firefly via the website without owning Photoshop, but the most advanced features are only possible when you subscribe to a Creative Cloud plan that includes Photoshop. You can learn more about Photoshop’s AI tools in Adobe’s blog post.

If you’re a subscriber, you can install the beta version (24.7.0) of Photoshop now from Adobe Creative Cloud Desktop. If you don’t have Photoshop, subscriptions start at $10 per month, making it affordable to explore what’s possible.

Firefly is being integrated into Adobe Express and Illustrator as well. Adobe Express will get an AI image generation feature that works within the browser, adding another tool to this quick and easy online image editor.

Adobe Illustrator fans will get AI features to cycle through various color palettes for their artwork using a prompt-based system. Adobe’s generative recolor uses AI to understand descriptive phrases and apply a matching theme to fills and strokes.

All of which makes Adobe more of a compelling solution to your image editing needs should you decide to find out how much Adobe Photoshop might cost. Then again, there are options for using Photoshop for free.

Alan Truly
Alan Truly is a Writer at Digital Trends, covering computers, laptops, hardware, software, and accessories that stand out as…
Topics
Adobe releases its first commercially safe Firefly video generating AI
Firefly video still shot of an Icelandic horse

Following on the success of its IP-friendly Firefly Image model, Adobe announced on Wednesday the beta release of a new Firefly Video model, as well as two subscription packages with which to access its audio and video generating abilities. Generate Video, according to the announcement post, "empowers creative professionals with tools to generate video clips from a text prompt or image, use camera angles to control shots, create professional quality images from 3D sketches, craft atmospheric elements and develop custom motion design elements."

The model will initially be able to generate video in 1080p resolution to start, though the company plans to release a 4k model for professional production work in the near future. Like the image generator, Firefly Video is trained exclusively on Adobe stock, licensed, and public domain content, making its outputs usable in commercial applications without fear of them running afoul of copyright or intellectual property protections. And, unlike Grok 2, there's minimal chance of it outputting racist, offensive, or illegal content.

Read more
You can now try out ChatGPT Search for free
The ChatGPT Search icon on the prompt window

As part of its "12 Days of OpenAI" event, OpenAI has yet another update for ChatGPT, this time bringing its Search feature over to the free tier. The Google Search alternative was previously only for paid subscribers in the ChatGPT Plus or Pro tiers.

"We rolled it out for paid users about two months ago," Kevin Weil, OpenAI's chief product officer, said during Monday's livestream. "I can't imagine ChatGPT without Search now. I use it so often. I'm so excited to bring it to all of you for free starting today."

Read more
OpenAI’s Advanced Voice Mode can now see your screen and analyze videos
Advanced Santa voice mode

OpenAI's "12 Days of OpenAI" continued apace on Wednesday with the development team announcing a new seasonal voice for ChatGPT's Advanced Voice Mode (AVM), as well as new video and screen-sharing capabilities for the conversational AI feature.

Santa Mode, as OpenAI is calling it, is a seasonal feature for AVM, and offers St. Nick's dulcet tones as a preset voice option. It is being released to Plus and Pro subscribers through the website and mobile and desktop apps starting today and will remain so until early January. To access the limited-time feature, first sign in to your Plus or Pro account, then click on the snowflake icon next to the text prompt window.

Read more