Adobe’s experimental AI tool can edit entire videos using a single frame

Adobe showed off some experimental AI tools it’s working on at its Max conference that provide new ways to intuitively edit photos, videos, and audio. These experiments, called “sneaks,” include tools that instantly apply any changes you make to a single frame across an entire video, easily manipulate light in photos, and correct mispronunciations in audio recordings.

Project Frame Forward is one of the most visually impressive tricks, 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 Frame Forward identifying, selecting, and removing a woman in the first frame of a video, then replacing her with a natural-looking background — similar to Photoshop tools like context-aware fill or background removal. This removal process is automatically applied across the entire video with just a few clicks.

Users can also insert objects into the video frame by drawing where they want to place them and describing what to add using AI prompts. These changes will be applied similarly to the entire video. The demo shows that these inserted objects can also be context-aware, showing a created shape that mirrors the movement of a cat that was already present in the video.

Another tool is Project Light Touch, which uses artificial intelligence to reshape light sources in images. It can change the direction of lighting, make rooms appear as if they are lit by lamps that were not turned on in the original image, and allow users to control the spread of light and shadow. It can also insert dynamic lighting that can be dragged across the editing panel, bending light around and behind people and objects in real time, like lighting up a pumpkin from inside, transforming the surroundings from day to night. The color of controlled light sources can also be adjusted, allowing you to adjust warmth or create vibrant RGB-like effects.

Project Clean Take is a new editing tool that can change how speech is pronounced using AI prompts, eliminating the need to re-record video or audio clips. Users can change the diction or emotion behind someone’s voice — making them sound happier or more curious, for example — or replace words entirely while maintaining the distinctive characteristics of the original speaker’s voice. It can also automatically separate background noise into individual sources so users can selectively tune or mute certain sounds, helping maintain the overall sound while improving voice clarity.

These are just a handful of the sneaks shown off at Adobe’s Max event. Other notable mentions include: Roof replacement projectwhich allows you to instantly change the material or texture of objects and surfaces, Project operating mode To edit objects in photos by rotating them as a 3D image, and New Depths Projectwhich lets you edit photographs as if they were 3D space by specifying when inserted objects should be partially obscured by the surrounding environment. You can read more about each preview in detail On the Adobe blog.

Adware is not generally available for use, and cannot be guaranteed to become official features in Adobe Creative Cloud or Firefly applications. Many features, such as Photoshop Remove distractions and Tool formatinitially started as hack projects, however, there is a good chance that some version of these experimental capabilities will be available to creators in the future.