Adobe is currently holding its MAX 2023 event, showing off what it has in store for the coming year. One of the focuses of the conference was a series of eleven “projects” that have the potential to become “major elements” of Adobe products in the future.
Recently, the company previewed one of these elements, called Project Stardust, which has the ability to separate objects in a photo into separate layers for easy editing. Users have the ability to move or delete objects. From there you can have a generative AI create something that can take its place. The other 10 occur just as they use AI technology to power their robust editing and creative capabilities. The group is divided into three main categories.
photos
Next to Stardust in the Photos category you have Project See Through, a tool that removes reflections in a photo. Adobe states that glass reflections can be very annoying because they can obscure subjects. Instead of having to edit the image in Photoshop in multiple steps, See Through does it all for you quickly.
Video and audio
Just as Stardust can remove objects in images, Project Fast Fill can remove them in videos thanks to the company’s Genative Fill technology. It can also add or change content via “Firefly-Powered Text Prompts.” In the example we see, Fast Fill can add a tie to a man whose suit is not provided, or change latte art in a cup of coffee from a heart to a flower.
#Adobe unveiled Project Fast Fill’s experimental #AI system brings Firefly’s Generative Fill to video, allowing artists to add or remove objects in footage using simple text promptshttps://t.co/7q6ZnCXVSv #AdobeFirefly #generativeAI #VFX #motiongraphics @ creativecloud pic. twitter.com/9PuVmqyam1October 11, 2023
Project Res Up can then increase the resolution of a clip via diffusion-based upsampling technology. Scene Change is the third and can change the background of a video from, for example, an office building to a jungle. For audio, there’s Project Dub Dub Dub, a software tool that claims to be able to translate speech from one language to another “while preserving the voice of the original speaker.”
3D and design
For the final category, these five are all about helping users create – even if they aren’t the best artists.
Project Draw & Delight can turn your doodle into a polished drawing using a text prompt to guide it. Glyph Ease “makes custom lettering more accessible” by applying specific design elements directly to a word in Illustrator. All you have to do is give a rough outline of what you want the AI to add.
The trio of 3D imaging software is more situational, but still impressive.
Project Poseable’s AI can adapt a 3D model to “poses from photos of real people.” So if you upload a photo of someone striking a karate pose, the model will do the same. Project Primrose allows artists to quickly change the texture of a rendered garment. And finally, we have Neo, which helps makers create 3D objects using “2D tools and methods.
To reiterate what we said earlier, these projects are prototypes at the time of this writing. There is no guarantee that these will become a new feature in Photoshop or any other Adobe product. However, there are a few that we think have the potential for an eventual release.
Stardust, Res Up and Draw & Delight seem the most “complete”. There are not as many visible flaws as with some others. In our opinion, certain projects require more time in the oven. For example, Dub Dub Dub’s voice sounds very stilted and robotic. It’s not natural.
Be sure to check out TechRadar’s list of the best AI art generators of the year if you’re looking for ways to boost content generation.