Adobe gets into the generative AI image game
Tools like DALL-E, which create images based on the text you type, have been buzzing on social media lately. But now Adobe, the behemoth of design, photo and video software, is also looking into this intriguing branch of AI technology.
As the company pointed out at its 2022 Max conference, the new features will appear as beta options in Photoshop, Lightroom, Premiere Pro and other apps that are part of the company’s Creative Cloud suite.
Adobe Unveiled 10 Projects Involving AI During Conference Sneaks(Opens in a new window) session:
Smart Composites Project: Turns the once tedious process of compositing images into backgrounds into a simple drag-and-drop process with automatic adjustments for color and shadows.
Instant add-on project: Simplifies the typically complex and time-consuming process of editing videos and adding VFX effects in post-production by using AI to automatically map graphics to the chosen element in the video.
Type of magnetic project: Allows anyone to instantly attach and merge any shape, even hand-drawn calligraphy, to a piece of live digital text.
Project vector edge: Provides designers and their teams with the ability to view, edit, and collaborate on 2D designs in 3D environments during the design process.
Motion Mix Project: Enables creators to easily create looping, high-quality human animations with realistic human movement, all from a still image.
Blink Project: Helps everyone quickly find and extract highlights from video content, making editing videos as easy as editing text. Project Blink is now available in beta and you can register to access it.
Art scenes of the project: Transforms 3D scenes using styles from 2D illustrations. Creators can quickly create high-quality, stylized 3D content that will be essential for the future of VR and AR experiences.
All about me project: Makes images without cropping a breeze. Leveraging AI, Project All of Me generates uncropped components of photos, removes unwanted distractions, and can even alter the clothing of the photo subject.
Project Beyond Seen: Easily generate full 360 degree panoramas from a single 2D image to create realistic and fully immersive 3D environments.
Project carried out in the shade:Allows users to move a person or object in a photo and cast realistic shadows, making editing 3D images simple and intuitive.
You can watch demos of the new technology on the Adobe Max Sneaks YouTube channel(Opens in a new window).
The most fascinating of these to me is Project All of Me, as well as those that create 3D scenes from 2D images (although CyberLink(Opens in a new window) did something like this many years ago when 3D video was a hot topic).
While it doesn’t completely generate an image from text like DALL-E and others do, All of Me doesn’t just replicate a consistent background, but actually creates body parts and clothing that do not exist in the original image.
At the Adobe Max conference, company executives also mentioned a Beta Neural Backdrop Filter for Photoshop, which will allow you to say to the software, for example, “Take me to Thailand” and then generate a back drop. -proper plan, or tell Lightroom to change a photo from day to night.
According to company press materials, “In Photoshop, generative AI will allow you to add new objects to an image, create variations based on your existing image, or even add a new section to your composite. simply by describing what you want.” He also mentions that Adobe Express will have generative AI features, although Canva already has a beta AI text-to-image generator tool.
Adobe has announced a slew of other new features for its software, which you can read about in our Adobe Max 2022 news article.
Receive our best stories!
Register for What’s up nowto get our top stories delivered to your inbox every morning.