Adobe previews precise AI editing projects at MAX

Nov 11, 2026
Adobe previewed three research projects that apply precise edits to images and video. Deep Brush and Hands-On will receive early access releases through Adobe Labs.

Following its broader Creative Cloud AI announcements at Adobe MAX, Adobe previewed three research projects for precise image and video editing, according to CNET. Project Deep Brush, Project Hands-On and Project Scene Sweep will be presented during the event's Sneaks session.

Project Deep Brush lets users apply text, paint and objects across uneven surfaces such as walls, fabric and skin. It adjusts edits to match an image's geometry, lighting and shadows, and can place them behind existing objects.

Project Hands-On analyzes an image, identifies editable objects and displays controls over them. Users can change properties such as shape, material, color and photo style, then apply multiple edits together.

Project Scene Sweep tracks a selected person across a video's timeline and applies prompted changes, such as a different hairstyle or jacket, across each shot. Deep Brush and Hands-On will receive initial public releases through the relaunched Adobe Labs website this week, while Adobe has not confirmed a public release for Scene Sweep.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.