Topaz Photo AI v1.4.1


This week we have a few new options regard Face Recovery. You now have the option to refine or not refine the hair and neck area for each face. Face Recovery should also now better preserve people’s eye colors.

Along with these we’ve also had several UI fixes and changes which are listed in the change log below.

Please give us any feedback or report issues with this release. We’ll be updating TPAI regularly to address those pieces of feedback and issue reports. If there’s a specific image you’d like us to see, you can send it us at this dropbox link.

Released July 13th, 2023
Mac: Download
Windows: Download

Note for MacOS users: The new minimum supported OS version is now 11.0 (Big Sur).

Changes since 1.4.0:

  • Fixed issue where Photoshop plugin would allow autopilot to upscale the image, which would make saving stall unless turned off
  • Face Recovery should now preserve eye color
  • Face Recovery has new options to recover or not recover hair and neck areas
    • You can find this under Preferences > Autopilot > Face Detection > Parts To Enhance
  • Various UI tweaks
    • Unit selector (PX/IN/CM) in upscale now highlights on hovered to indicate it’s interactable
    • Unit selector popup should now properly show all options without elision
    • Comboboxes in preferences no longer blend into the background when clicked
    • Fixed minor visual issues in update dialog
    • Renamed “Close” option to “Close Image” in right click menu to be more clear on what it’s closing
  • Fixed canceling export not canceling processing
  • Fixed CLI not upscaling
  • Fixed some pixel unit conversions when using PPI/PPCM
  • Fixed resolution units not being read when using external editors

Known issues:

  • If you have a width/height set via Autopilot, the upscaling enhancement label might push the toggle out of bounds.
  • Text refinement may crash on some Nvidia cards. This should be resolved next week.


Hi Adam, Thx for the update.

I’m sending a clock image via Dropbox that worked very well in PAI prior to 1.4.x. Now the denoising and sharpening are stripping out/smoothing beyond recovery key image details. And, adding ‘jaggies’.

In fact, when I 1st used the image for testing, PAI made it look magnificent and almost 3D. Now it looks like a watercolor that someone spilled water on. Perhaps the denoise/sharpen sensitivity needs a tweak. (I always try all models and various slider strength levels + denoise/sharpen off-on…). Win 11 Pro. Standalone & Ps Plugin.


Later: After hunting to figure out which (beta) release produced the excellent processing and detail - including text. I looked thru the various discussions & can’t find the post to determine which rel. it was. But here’s a copy of the PAI post-processed same image with that earlier release. Converted to a monochrome. Look at the signif. differences in the details… including the earlier rel even made something of the Breguet jewelers mark near the 6-7 hours. [In my personal files I found this as having been processed with whatever curr. beta rel. was in progress on Jy. 1].

1 Like

Still getting the phantom half pair of glasses. Can we add a no glasses option to the hair and neck face recovery preferences?

Also, for images with multiple faces would it be too much to ask for the preferences to be selected differently for different faces? Some images will have one central face where hair and neck recovery are absolutely needed, but it may not be desirable for others in the periphery.

Here’s a better picture of Mr. Myron Fuller Davis about 1893.


Testing vintage face recovery. In both, faces are very good, in one, neck and hair were not recovered despite the settings.


Great :slight_smile: :+1:

But there are still a few Issues:

Some Hair-Areas are not detected and are still unsharp…
Could you maybe implement a “Quick Select”-Tool for the FaceDetection to manually select Areas, which are not automatically detected (like in the “Preserving Text”-Tool)?

There are some Cases where still strange Artifacts appear on the Face, Teeth, Nose etc…


Can anyone show me where this new face feature is, the refine/not refine the hair/neck area for each face? I cannot see any additional controls.

In preferences cycles between Hair, Neck and Hair Neck:


In Preferences I have Upscale output size set to 2000px Height however when opening images the height in Upscaling varies between 1998px to 2004px. It is correctable by manualing setting it each time but that defeats the purpose of my default setting in Preference.


I tested the latest release version on a low quality, highly pixelated looking screenshot with some symbols and text and once again TPAI surprised me with a perfect looking result. :blush:



See above.

I told you a lot of users don’t check, don’t know about Prefs.

Okay but any serious app has preferences settings. I’d say, users will learn sooner or later.


I am a bit confused about the upscaling option. Dependend on which photo I open it seems to randomly choose an upscaling factor itself. :eyes:

If you have Upscale in Preferences set to “Enhance small images” or a scale factor and the input files have different dimensions, the outputs will have different sizes


For what I do, this is performing quite well.

TPAI v1.4.1 still errors out trying to open a TIFF created by DxO Photolabs 6.8.0 Build 53.

Mac M1 Max. Nikon NEF file.

Chromatic aberration correction is not applied for Sharpen/Strong:

It is slightly applied for Sharpen/Standard:

It is excellent for Sharpen/Lens Blur:

It is excellent for Sharpen/Motion Blur:

Original without Sharpen:


Yes, I’m happy that they brought back the lens blur and motion blur options. In certain cases these filters also render crispier results.

This update does not correct the bug that causes the software to freeze when using the text preservation filter.


Im still seeing the issue with random batched file names saving with the wrong name, causing destructive overwrites and duplicated images

Artifacts - Sharpen/LensBlur