Adobe revealed a suite of experimental AI-powered tools at its annual Max conference today, showcasing features that can convert flat images into navigable 3D environments, develop AI characters through spoken dialogue, and automate photo editing across multiple subjects. The "sneaks" — technology previews that may eventually launch in Adobe's Creative Cloud apps or Firefly platform — represent the company's latest push to make complex creative workflows more accessible through generative AI, according to a report from The Verge. While there's no guarantee these experimental features will become available products, almost all are built on Adobe's generative AI developments, which now play a central role in the company's growth strategy.
Among the showcased tools, Project Sight Span reframes photographs and images by converting them into 3D spaces that users can navigate and reposition. The feature generates objects and backgrounds beyond the original frame that feel like natural parts of the image, even allowing users to turn around and see what's behind them. While the 3D environment displays pixelated and ill-defined visuals, the resolution quality restores when users select their chosen angle. The tool works with any flat image — including photos, paintings, and illustrations — and can preserve and replicate artistic styles, with repositioned tattoos and facial features in photographs remaining recognizable and true to the original reference. Project Screen Test takes a different approach by letting users develop AI-generated characters through conversation rather than text prompts alone. Users start by describing base personality traits such as "anxious, shy, awkward" and selecting a voice through presets, prompts, or uploaded audio samples, then expand the character's persona by conversing as if on FaceTime to outline backstory, temperament, goals, flaws, fears, and movement quirks. Once complete, the tool generates animated screen tests with the character in user-described environments or scenarios. Project Sound Bender enables users to customize sound effects by uploading a video clip and describing desired audio in text prompts like "bubbling sci-fi cauldron noises," with the tool generating effects that automatically sync to the video and providing a square sound canvas for real-time adjustments. Each corner of the canvas assigns a relevant AI-generated sound — such as dense gurgling with popping bubbles, rumbling boiling rocks, pitched bloops, and crackling electric fire — with users dragging their cursor to select which noises stand out most or customizing each corner with different effects. Meanwhile, Project Rinse Repeat lets users copy edits and automatically apply them to other objects or people in the same photo, such as painstakingly airbrushed acne or blemishes on one person that Rinse Repeat will adapt to anyone else in a group who needs similar touchups.
The report notes that Project Screen Test provides a more identifiable and consistent personality compared to many soulless animated AI characters, but that's the entire reason it exists — AI video generation provides far less creative control compared to traditional animation, where every aspect of a character is included with absolute intention. The results for Screen Test are currently a standalone creative exercise, and it's unclear how or if the feature could integrate into any of Adobe's existing AI video tools. Project Rinse Repeat is built around Photoshop, and the edits applied to other subjects remain fully editable because the tool recreates them with native Photoshop tools, allowing users to add shadows to products in marketing graphics even if the objects are different shapes and sizes. "Making these interactions more intuitive is also about giving experienced creatives more precise control," senior principle Adobe research scientist Gautham Mysore told The Verge, noting that "Sound Bender's sonic exploration capability and Sight Span's camera positioning are examples of how professionals could apply their judgment and refine a result more directly."
The report explains that a notable theme across these sneaks is making complicated photo editing, filmmaking, and audio mixing workflows feel more accessible and intuitive, adapting them into something more interactive and easy to use. In some cases the features almost seem like toys, but with the benefit of allowing practical changes to creative projects. That connection between creative intent and control is a big part of what Adobe's exploring with these experimental tools. As wacky or fun as these AI experiments are, they're also an omen — if they're useful enough, that means AI may eventually replace the tools and stock libraries that creative professionals currently use, regardless of how complex their feelings are about the technology. The company's focus on translating professional-grade capabilities into more conversational interfaces signals a bet that lowering technical barriers won't just expand the user base, but fundamentally reshape how creative work gets done. Whether that transformation empowers professionals or undercuts their specialized skills will depend entirely on how Adobe balances automation with the granular control that separates craft from convenience.