Follow along with the video below to see how to install our site as a web app on your home screen.
Note: This feature may not be available in some browsers.
Full disclosure: I’m a PureRAW/Lightroom user myself.
There was a major improvement with the latest updates of Topaz AI.Full disclosure: I’m a PureRAW/Lightroom user myself.
I find it interesting that the main differences are in tone and saturation rather than noise and sharpness. In this particular example I think I prefer the Topaz one although in my testing with my own images it has always gone the other way.
either way love the guy sleeping to the left of the plant…or is he enraptured ?
No doubt! All the modern tools recover two stops of ISO noise. Before I’d never shoot above 1600. Now I can push to 6400 when I nail the exposure and 5000 fairly reliably. Really makes the 1” sensor.…improved over what the camera could do with its jpeg.


I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.

Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
But there's another problem. DeepPrime XD looks like it has tried to sharpen these background faces that are obviously out of focus due to the photo being taken at 600mm equivalent zoom. Whereas Topaz AI has rendered them correctly.Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
Yes, agreed. I wonder if different settings in PL6 might have produced a better result (eg, using DeepPRIME, not XD)?But there's another problem. DeepPrime XD looks like it has tried to sharpen these background faces that are obviously out of focus due to the photo being taken at 600mm equivalent zoom. Whereas Topaz AI has rendered them correctly.Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
Quite possibly. Perhaps Tom could make the raw file available?Yes, agreed. I wonder if different settings in PL6 might have produced a better result (eg, using DeepPRIME, not XD)?But there's another problem. DeepPrime XD looks like it has tried to sharpen these background faces that are obviously out of focus due to the photo being taken at 600mm equivalent zoom. Whereas Topaz AI has rendered them correctly.Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
I'd be happy with either of those images.I've been using both DxO PhotoLab and Topaz Photo AI for longer than you have, and that doesn't look like a characteristic Topaz Photo AI result. It normally removes nearly all traces of noise. Often I choose to override the Autopilot settings to allow a little noise back in.
Here's an ISO 5000 shot of mine, processed from an RX100M3 ARW file:
DxO PhotoLab with Standard preset and DeepPRIME noise reduction set to 100
Topaz Photo AI with Autopilot settings (Remove Noise: Strong, Strength: 8, Detail: 82)
Yes, colors are richer with Photolab, which is a full featured RAW converter. Photo AI is not a full featured RAW converter, so I don't use it that way. My normal use of it is only on edited raster images like JPEGs or TIFFs that might need extra help with noise and/or sharpening.
Out of curiosity I searched and found the two 'stuck white pixels' (it's raining outside) and zoomed them up in Photoshop. In both cases, the defect spreads out to surrounding pixels. Would a single dead pixel produce that effect?An interesting observation: The Photo AI version shows a couple of stuck white pixels. PhotoLab's dead pixel correction found them and fixed them.


The fact that you have been using Topaz longer than I have doesn't matter because the latest versions of Topaz make earlier versions obsolete with all the recent upgrades. I have to upgrade Topaz about every 2 or 3 weeks. Previously the difference between Topaz and Photolab was very obvious but with the latest upgrades I installed a few days ago, they are closer. DXO however is my go-to RAW editor because it's full-fledged whereas Topaz has limited controls and relies more on AI for everything.I've been using both DxO PhotoLab and Topaz Photo AI for longer than you have, and that doesn't look like a characteristic Topaz Photo AI result. It normally removes nearly all traces of noise. Often I choose to override the Autopilot settings to allow a little noise back in.
Here's an ISO 5000 shot of mine, processed from an RX100M3 ARW file:
DxO PhotoLab with Standard preset and DeepPRIME noise reduction set to 100
Topaz Photo AI with Autopilot settings (Remove Noise: Strong, Strength: 8, Detail: 82)
Yes, colors are richer with Photolab, which is a full featured RAW converter. Photo AI is not a full featured RAW converter, so I don't use it that way. My normal use of it is only on edited raster images like JPEGs or TIFFs that might need extra help with noise and/or sharpening.
An interesting observation: The Photo AI version shows a couple of stuck white pixels. PhotoLab's dead pixel correction found them and fixed them.
I have no way of making the RAW file available but when I have a chance I will post a few samples with different settings.Quite possibly. Perhaps Tom could make the raw file available?Yes, agreed. I wonder if different settings in PL6 might have produced a better result (eg, using DeepPRIME, not XD)?But there's another problem. DeepPrime XD looks like it has tried to sharpen these background faces that are obviously out of focus due to the photo being taken at 600mm equivalent zoom. Whereas Topaz AI has rendered them correctly.Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
Yes, I believe you are correct.But there's another problem. DeepPrime XD looks like it has tried to sharpen these background faces that are obviously out of focus due to the photo being taken at 600mm equivalent zoom. Whereas Topaz AI has rendered them correctly.Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
That is correct.Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
I used Deep Prime XD which tends to produce more artifacts than Deep Prime but it does reduce the noise more.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
I suspect DeepPRIME might have been the better choice with this example. And you should always turn down the Noise model with XD (I suggest -40).I used Deep Prime XD which tends to produce more artifacts than Deep Prime but it does reduce the noise more.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()
That's a pity. Would have liked to give it the once over with Adobe Denoise in Lightroom.I have no way of making the RAW file available but when I have a chance I will post a few samples with different settings.Quite possibly. Perhaps Tom could make the raw file available?Yes, agreed. I wonder if different settings in PL6 might have produced a better result (eg, using DeepPRIME, not XD)?But there's another problem. DeepPrime XD looks like it has tried to sharpen these background faces that are obviously out of focus due to the photo being taken at 600mm equivalent zoom. Whereas Topaz AI has rendered them correctly.Yes, that suggests use of DeepPRIME XD without turning down the Noise model.I prefer the Topaz image. The artifacts produced in the DxO image are unacceptable to me.
Here's a 100% crop example.
![]()