• Please use real names.

    Greetings to all who have registered to OPF and those guests taking a look around. Please use real names. Registrations with fictitious names will not be processed. REAL NAMES ONLY will be processed

    Firstname Lastname


    We are a courteous and supportive community. No need to hide behind an alia. If you have a genuine need for privacy/secrecy then let me know!
  • Welcome to the new site. Here's a thread about the update where you can post your feedback, ask questions or spot those nasty bugs!

Digital Processing Issues and Fixes: Topaz sneaks out Gigapixel AI update, 3X faster

Yesterday Topaz soft-released version 4.3.1 of Gigapixel AI, with the following features:

•Toggle in right panel to enable and disable Face Refinement

•Face Refinement will detect small faces (16x16px - 64x64px) and apply targeted improved upsampling

They are also aiming for 3X faster CPU processing.

Below is a screenshot of the new GUI with a 15-year old, 4MP image being treated with 4X magnification.

Last edited:
Thanks, I thought so too, considering the small area of the full image being processed.

See my blog (URL in sig) for more examples (including some fun ones!)
Update: Version 4.3.1 is being revised due to some issues with the Mac version (although the copy I updated to a few days ago still works fine), so watch for news in the next couple of days.

Asher Kelman

OPF Owner/Editor-in-Chief
Have you tested it? 3x faster is a huge improvement. What does it require to get that extraordinary benefit?

This speed increase effort was aimed at CPU mode (which I never use, as my mighty MacBook Air has a decent GPU ;-)), but I am about to have some fun on a 17" 2008 MacBook Pro running Mojave...
Turns out I had Gigapixel 2.1.1 on the old MBP (which I successfully updated to 4.3.1), but we want to test 4.2.2 vs 4.3.1 in CPU mode. I was unable to do that as my main computer already had the latest version.

The official 4.3.1 release change log states:

Third party libraries for Gigapixel
Qt libraries
Lensfun Library
AI Model Update

If someone still has 4.2.2 installed and hasn't updated yet, please test in CPU mode vs. 4.3.2!