BRAHMA AI's Face Replacement Tech De-Aged Hanks on Set in Near Real Time

September 10, 2026
BRAHMA AI's Neural Performance system changes a performer's age or likeness while preserving facial timing and expression, and delivered about an hour of final 4K for the film Here. It has now shared a Technology and Engineering Emmy.

BRAHMA AI's Neural Performance technology changes a performer's age, likeness or identity while retaining facial timing, gaze, expression, lighting and movement, including under changes of pose and occlusion, the company said in a press release.

It was used on Robert Zemeckis's film "Here" to show younger versions of Tom Hanks and Robin Wright on set in near real time, and produced about one hour of final 4K transformation for the finished film. The technology also provides English language lip sync for "Ramayana" that preserves the original performance. Its core methods are covered by US Patent No. 12,322,018.

The work has now received a 2026 Technology and Engineering Emmy Award for AI based face replacement and performance preserving post production transformation, shared with Disney Research, Rising Sun Pictures and Digital Domain. The ceremony is on October 14 at the Television Academy's Saban Media Center in North Hollywood, California.

We hope you enjoyed this article.

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

Also, consider following us on social media:

AI Brief AI Brief (X)

Subscribe to Daily AI Brief

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

AI Token Webinar

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

You May Also Like