At Max, Adobe demonstrated some of the experimental artificial intelligence tools it is working on that provide up-to-date ways to intuitively edit photos, videos and audio. These experiments, called “tricks,” include tools that instantly apply any changes made in a single frame to the entire video, easily manipulate delicate in images, and correct pronunciation errors in audio recordings.
Project Frame Forward is one of the more visually impressive features, allowing video editors to add or remove anything from footage without using masks – a time-consuming process of selecting objects or people. Instead, Adobe’s demo shows that Frame Forward identifies, selects and removes the woman in the first frame of the video, then replaces her with a natural-looking background – similar to Photoshop tools like contextual fill or background removal. This removal will be automatically applied to the entire video in just a few clicks.
Users can also insert objects into a video frame by drawing where they want to place them and describing what to add with AI suggestions. These changes will be similarly applied throughout the video. The demonstration shows that these inserted objects can also be context-aware, showing a generated puddle that mirrors the movement of a cat that was already in the video.
Another tool is Project Featherlight Touch, which uses generative artificial intelligence to change the shape of delicate sources in photos. It can change the direction of lighting, make rooms look as if they were lit by lamps that were not turned on in the original image, and allows you to control the dispersion of delicate and shadow. It can also insert energetic lighting that can be dragged around the editing area, bending delicate around and behind people and objects in real time, for example, illuminating a pumpkin from the inside and changing the environment from day to night. The color of these manipulated delicate sources can also be adjusted, allowing you to adjust the heat or create colorful RGB-like effects.
Project Spotless Take is a up-to-date editing tool that can change the way speech is delivered using AI suggestions, eliminating the need to re-record video or audio clips. Users can change the delivery or emotion behind someone’s voice – for example, make them sound happier or more curious – or replace words entirely while retaining the characteristics of the original speaker’s voice. It can also automatically separate background sounds into individual sources, so users can selectively adjust or mute specific sounds, helping to preserve the overall sound while improving voice clarity.
These are just a few of the announcements made during the Adobe Max event. Other notable mentions include Replacing the design surfacewhich allows you to instantly change the material or texture of objects and surfaces, Design return style to edit objects in images by rotating them like a 3D image and New Depths Projectwhich allows you to edit photos as if they were 3D space, which identifies when inserted objects should be partially obscured by the surrounding environment. You can read more about each preview in detail on the Adobe blog.
Teasers are not publicly available and there is no guarantee that they will become official features of Innovative Cloud or Adobe’s Firefly app. However, many features like Photoshop’s de-distraction and harmonize tools started out as hidden projects, so there’s a good chance that some version of these experimental capabilities will be available to creators in the future.