Adobe Photoshop has been the gold standard in photo editing for over three decades, so it was only a matter of time until it embraced the tricks found in best AI art generators – and it’s now done in the form of a new tool called Generative Fill.
The new tool, which allows you to expand images or add objects to them using text prompts, is definitely not the first AI-powered feature we’ve seen in Photoshop. Generative Fill is also a user-friendly improvement on existing Adobe tools, such as Content Aware Fill, but it’s also one of the most significant new Photoshop features we’ve seen in years.
That’s because it relies on the power of Adobe Firefly, the company’s new generative AI engine, to help you fix major composition errors or completely reinvent image content. In Adobe’s demos, images in portrait orientation are instantly transformed into one of the landscape – with Photoshop simply inventing the sides of the photo based on the original image.
While some of the examples are quite subtle, others have a very clear artistic aesthetic. For example, a photo of a corgi turned into one with clearly fake bubbles and a van in the background.
Adobe clearly sees Generative Fill as a tool for both beginners and pros, but the new text-to-image prompt box is definitely a useful touch for those unfamiliar with existing tools. in Photoshop. You can use it to add small details to an image or completely change its background – in another demo, a deer was transferred from a forest background to a city thanks to the quick ‘wet corner of the night’.
Of course, none of this is new to fans of Midjourney or Dall-E, who helped fuel this year’s rise in the text-to-image generation.
But Adobe is keen to emphasize that AI tools like the Generative Fill model are only trained on Adobe Stock images, open licensed content, and public domain content where copyright has expired. This means that they can be used for commercial use without the threat of class-action lawsuits from artists who claim that certain AI models have stolen their work.
While Generative Fill is only rolling out to the entire Photoshop app in the “second half of 2023”, there are a few ways you can try it out now. First, it’s available in Photoshop’s desktop beta app, which you can get by going to the Creative Cloud desktop app, selecting Beta apps in the left sidebar, then installing it from there.
The feature is also available as a module within the web-only Adobe Firefly, which was also recently added to Google Bard. To use Bard’s Firefly, you can write your image request (for example, ‘create an image of a unicorn and a baby shower cake’) and it will do the rest. What a time to live.
Analysis: Photoshop takes on new AI rivals
Like Google, Adobe is an incumbent giant under attack from AI upstarts like OpenAI and Midjourney. While Firefly and Photoshop’s Generative Fill don’t do things we haven’t seen before, they do so in a way that avoids any copyright issues and helps maintain its reputation.
Photoshop’s embrace of generative AI has also brought these tools fully into the mainstream. The image editor may not have been the dominant force before the likes of Canva, Affinity Photo and GIMP arrived to offer more affordable alternatives, but it remains one of the best photo editors around and is certainly one of the most widely used.
From Adobe’s early demos, it looks like Generative Fill is in its early days and produces mixed results, depending on your preference. In some images, the effects are subtle and realistic, while in others – especially images where many parts are completely AI-generated – the results are clearly AI-generated and may look dated.
However, the arrival of Generative AI along with other new features such as the Remove Tool -another improvement on Photoshop’s existing ability to let you eliminate unwanted objects – is just one good thing for those unfamiliar with the app’s arcane interface.
And this is another step towards AI tools, like DragGAN, that will completely change photography as we know it.