Some of the most impressive technologies that Adobe shows off at its annual Max conference each year are the experimental features it’s developing, and the latest of those tools is being announced today: They can transform images into explorable 3D scenes, design AI characters by talking to them, and turn photo editing into a copy-and-paste process.
The first (and strangest, in my opinion) is Project Screen Test, which is designed to make AI-generated characters easier to develop and use for video content. Instead of simply describing how the character should sound and behave in text prompts, the tool allows you to talk to and direct the character in an audition-like environment. Start by describing some basic personality traits, such as “anxious, shy, awkward,” and giving the character a voice, either by selecting a preset, describing how they sound in a message, or uploading sample audio for reference.
You can then expand on their personality in more detail by chatting with the character as if you were talking on FaceTime, describing their backstory, temperament, goals, flaws, fears, movement quirks, and more. Once you’re happy, the tool allows you to generate animated screen tests with the character describing the environment or scenario you want to place them in.
This is currently a standalone creative exercise and it’s unclear how (or if) it might appear in any of Adobe’s existing AI video tools. The results provided a more identifiable and consistent personality compared to many soulless AI animated characters I’ve seen, but that’s the only reason this exists: AI video generation provides far Less creative control compared to traditional animation, where every aspect of a character is included with complete intention.
There’s also Project Sight Span, which reframes photographs and images into a 3D environment that you can navigate and reposition. 3D space generates objects and backgrounds that are outside the original frame, but feel like a natural part of the image, even if you turn to see what’s behind you. While the images in the 3D environment are pixelated and poorly defined, the resolution quality is restored when you select the chosen angle.
Sight Span works with any flat image, including photographs, paintings and illustrations, and can preserve and replicate artistic styles. Even the tattoos and facial features repositioned in the photographs remain surprisingly recognizable and faithful to the original reference. It’s a bit like a version of Apple’s Spatial Reframing feature on steroids: you can reposition more aggressively and change the shooting point entirely if you want, but it also feels much less worthy of being called a photo afterward.
Project Sound Bender is an AI audio mixing feature that lets you customize sound effects as if you were clicking your cursor around a color wheel. It works by uploading a video clip and then describing the desired audio in a text message, such as “sci-fi cauldron bubbling noises.” Sound Bender then generates sound effects and automatically syncs them with the video, and provides a square sound canvas that allows you to adjust noises in real time. Each corner of the canvas will automatically be assigned a relevant AI-generated sound, such as a dense gurgling sound with popping bubbles, rumbling boiling rocks, high-pitched bangs, and crackling electric fire. You can drag your cursor around the canvas to select which noises stand out the most or customize each corner with different sound effects.
Adobe also introduced Project Rinse Repeat, which lets you copy edits and then automatically apply them to other objects or people in the same photo. For example, if you carefully remove one person’s acne or blemishes, Rinse Repeat will tailor your specific changes to anyone else in a group of people who needs similar touch-ups. It can also be used to add shadows to products in marketing graphics, even if the objects have different shapes and sizes. Rinse Repeat is based on Photoshop and the edits you apply to other subjects remain fully editable because the tool recreates them with native Photoshop tools.
These “stealth” are technological advances of capabilities that could They will eventually become tools for Adobe’s Creative Cloud apps or the Firefly platform, so there’s no guarantee they’ll become available features. Almost all of these projects are based on Adobe’s generative AI developments, however, and with AI tools now playing a central role in the company’s growth strategy, it is likely that at least some of the experiments will see an official release. As outlandish or fun as these AI experiments are, they are also a harbinger. If they’re useful enough, that means AI may eventually replace the tools and libraries creative professionals currently use, regardless of how complex their feelings about the technology are.
A notable theme in these advancements is making the complicated workflows of photo editing, filmmaking and audio mixing seem more accessible and intuitive, adapting them into something that is more interactive and easy to use. In some cases, the features almost feel like toys, but with the advantage of allowing you to make practical changes to creative projects.
“Making these interactions more intuitive also means giving experienced creatives finer control,” said Adobe Principal Research Scientist Gautham Mysore. The edge. “Sound Bender’s sonic scanning capabilities and Sight Span’s camera positioning are examples of how professionals could apply judgment and refine a result more directly. That connection between creative intent and control is a big part of what we’re exploring.”
