AI Photo Editor Review: Hands-On With Adobe Photoshop Generative Fill

The second main question on this topic is whether or not you as a photographer can legally stop someone from using your work as the basis of new work that is expanded using Generative Fill. That policy statement actually points to a case PetaPixel covered earlier this year, Yakov Livshits where the Office rescinded a copyright it had granted to an AI-generated comic. But that’s just the beginning — if you really want to go for it, you can go for it. Let’s take a little journey from beautiful-yet-deadly waterfalls to a beautiful-yet-deadly glacier.

Without wasting any time, here’s a quick look at what Generative Fill in Photoshop can do for your images. Later, I’ll also show how you can enable the feature to use it on your own computer. I mean sometimes you want an old photograph to look like an old photograph, but if you’re restoring images for archival purposes, this looks like Yakov Livshits an incredible timesaver. See below for the best current prices on Photoshop or see our guide to how to download Photoshop. We also have guides to the best Photoshop tutorials and the best free Photoshop actions. For the Generative Fill tool to function properly, the selection of the area where you want the fill to occur must be closed.

Expanding an image with AI

Accessing photoshop AI generative fill is super straightforward. If you’ve already got one, feel free to jump down to the next step. Describe the object or scene you wish to generate in English. It’s also possible to leave this box blank, allowing Photoshop to fill the selection based on the surrounding context.

Once downloaded and installed, open Photoshop (beta) and either click New File to start with a blank canvas, or drag and drop an existing image into the application window. For this demonstration we’ll be using a couple of different photographs, both taken recently with an iPhone and not previously edited in any way. There are lots of AI tools already capable of doing this, and here are the best AI art generators for 2023. But now Adobe has added a new function called Generative Fill to the latest Photoshop beta, more people than ever can experiment with AI-powered artwork and image editing. Generative fill allows designers to “quickly create, add to, remove or replace images right in Adobe Photoshop”. Similar to other AI image applications on the market, this feature only requires a simple text prompt to run.

Rework your images

If you wish your image was bigger, that it fit a wider or taller aspect ratio, or just had more in it, the generative fill command is super handy. Just take any picture, select where you want the tool to generate new content, and hit the button. You can even give it a text prompt to help explain what you want to see. Face it, the world has more than enough photos of almost everything , photography has already died for most aspects apart from what was once looked down on wedding or portrait photography of families.

• If you need to fill a large area, consider breaking it down into smaller sections and applying Generative Fill separately to each section.
• Learn how to get access, prompting tips, and how to utilize Firefly’s interface.
• These fast generative credits allow you to go ahead and use AI feature at full speed.
• The only copyrightable material was the text, which did not involve AI at all.

Available exclusively in Beta versions of Photoshop (for now), Generative Fill uses the power of AI to replace objects, change backgrounds, and more. We’ve seen people using Photoshop Generative Fill to make incredibly fast transformations to images, changing backgrounds and replacing objects with others. But Adobe ‘design evangelist’ Howard Pinksy has demonstrated on Twitter just how fast it can make the task of restoring old photographs, using generative AI to ‘fill in’ parts of the image obscured by damage.

Yakov Livshits
Founder of the DevEducation project
A prolific businessman and investor, and the founder of several large companies in Israel, the USA and the UAE, Yakov’s corporation comprises over 2,000 employees all over the world. He graduated from the University of Oxford in the UK and Technion in Israel, before moving on to study complex systems science at NECSI in the USA. Yakov has a Masters in Software Development.

Try as I might, I couldn’t get the AI to do a beam of light that fit the scene. It gave me a big block of green, a couple of stripes, and a metal tube. Again, I would have preferred some motion blur, but since I was limiting the act of jubilant creativity to just the Lasso tool and Generative Fill, there was no beam of light and no motion blur. Also, notice how the smokestack on the right side of the image is behind the foreground tree. For some reason, the AI decided to put a cluster of buildings kind of mashed on top of each other, sticking out from behind the bus.

To avoid this issue, try selecting a smaller area for the Generative Fill tool to process. If you need to fill a large area, consider breaking it down into smaller sections and applying Generative Fill separately to each section. B&H – B&H is a world renowned supplier of all the gear photographers, videographers, and cinematographers need and want to create their very best work. Mylio Photos – Access your photos from anywhere, without the cloud! Easily showcase your photos on-the-go, resolve duplicates, find faces and look for those stunning locations.

Here’s what the valley carved out by the glacier actually looked like, and here’s what I got when I asked Generative Fill to make it even more ominous by adding a thunderstorm. By Allison Johnson, a reviewer with 10 years of experience writing about Yakov Livshits consumer tech. She has a special interest in mobile photography and telecom. Right now, there’s plenty of hand-wringing over the damage artificial intelligence (AI) can do. The uses for this tool are potentially endless in the right hands.

Even though there are only a few, these tools will save designers a ton of time editing low-quality or unattractive photos. The edits Generative Fill makes aren’t always perfect, showcased by examples created by a writer for The Verge. But as with other photo editing services like those announced by Google earlier this month, the technology is designed to learn and improve over time. Generative Fill is built into every selection feature in Photoshop, and Adobe has created a new generative layer type for non-destructive work. This tool allows users to add, remove or replace parts of an image, and extend the edges of an image simply by using their natural language to prompt Photoshop. For example, users can type a description like “big brown bear sitting down”, and the AI will generate the content accordingly.

I might consider using Generative Fill in the future to remove unwanted hot spots or minor issues such as graffiti with profanity or other unwanted elements. I suppose that means that my photo might be flagged with an invisible digital signature to indicate that it is created by AI. This of course blurs the lines between AI-generated art and photography. Then again, on a purely technical level, many feel that Lightroom Denoise AI or Topaz Labs Denoise AI already do this. Adobe says that creators produced over 1 billion AI-generated assets using Photoshop beta’s generative fill feature alone.

But you can’t assume that the feature will get it right every time. Strangely, in multiple attempts the tool assumed that we wanted to replace the person with another, random, person. And these were nightmare-inducing renditions of synthetic people. Some extra canvas was created to the right of the image above and the Generate button was clicked when the text prompt box was empty.

Tapping into machine learning technologies, Photomator is a photo editor that offers a step up from Apple Photos and an affordable alternative to Lightroom. I find the auto selection tool for subject is very accurate in both Photoshop and Lightroom. What annoys me with AI applied to photography is that the whole point is to hide the manipulation, so as to fool the viewer more comprehensively and easily than ever. That offers us “choice”, as you say, but not the kind of choice conducive to photography, which is a process based on reality rather than a final product presented as reality. AI is an extra tool if you want to produce images, but image production is not photography. That being said, as an amateur photographer I don’t think that this kind of functionality is truly essential in any shape or form because this ain’t photography anymore but creative image generation.