Artificial Intelligence on PhotoLab: what do you expect for?

Alec, can I just ask how you might go about creating the Orton Effect, which seems to involve all sorts of multiple layer manipulation in Photoshop but I believe should be possible in PL using local adjustments?

I have made a simple first attempt and it’s “sort of” OK(ish) but was wondering if anyone had already done something like this?

1 Like

Someone did create a preset. I have it. It works better on some images than on others. I’m not at home right now, but I’ll upload it when I get a chance


That’ll be me :stuck_out_tongue_winking_eye:

I was having a discussion with some friends and they were adamant that I couldn’t do the same as Photoshop because PL doesn’t have layers but I began to think that local adjustments can be “layered” and was trying to use that idea instead of just flat global adjustments.

1 Like

Sorry, I didn’t recall that it was you who created it. I’ve used it a few times to try to create that dreamy orton effect. As I indicated, In my experience it works better on some images than on others.


Interesting question, Joanna. If I were after the Orton Effect in its traditional form, I’d export two versions from Photolab and then combine them as layers in Affinity Photo (which has a dreadful RAW module but is otherwise an extremely powerful, and high performance bitmap editor, and replace Photoshop perfectly except for compatibility with some Photoshop plugins.

If I were trying to add a pseudo-Orton Effect, I’d pick the places I want diffusion and glow and use U-point and local adjustments. I’m not big on diffusion and glow in my own work so I haven’t wrestled with the problem in earnest.

1 Like

Autumn 2023 update:

Of all the proposed AI applications, let’s take stock:

#1 AI mask: now in Capture 1 and Lightroom!

When I see their demos, the edges of the selected areas are very sharp. Usually, it is difficult to get a convenient result with this kind of selection. I found the Control lines and the U-points of PhotoLab easier to handle for photography.

#2 AI highlight recovery: still pending, and I think (hope) a huge improvement is possible on this point.

#3 AI auto-fill: now in Photoshop! It seams that AI generative features are not in the spirit of PhotoLab…

#4 AI noise reduction: done! That’s DxO DeepPRIME and DeepPRIME XD! But now, Lightroom and Topaz have similar proposals, even if they are less performing in my opinion).

#5 AI DAM assistance: in place or in the process of being implemented in all DAM software.

#6 AI auto-clean up of sensor dust: this is really what I’m looking forward to the most.

#7 AI-help for editing (automatic multi-criteria scoring/notation aid).

#8 AI object detection and replacement: already available in Luminar Neo and Google smartphones!

#9 AI luminosity, automatic white balance on a series of pictures.

#10 AI super resolution. Already available in Topaz! Combined with DeepPRIME, this features would give a new youth to old pictures, from 6-10 Mpix cameras. A smart way to merge old pictures with new ones.

#11 AI Auto HDR, from one picture or a series.

#12 AI blur-removal: already existing in Topaz Sharpen-AI, but it could be a nice improvement for PhotoLab.

#13 AI improvements for Auto-horizon, Auto-perspective. Really, actual tools are very poor in auto mode in PhotoLab. They deserve some improvement.

#14 AI lens blur simulation, that I discovered with Lightroom. AI generates a 3D-map of the image to create an artificial bokeh with realistic blur transitions + predefined bokeh styles (circles, rings, cat eyes, and so on). Interesting concept.

My vote:

  • First, compatbility with dng of smartphones. It is not AI, but I really miss it.

  • Second: #6 AI auto-clean up of sensor dust.

  • Third: #2 AI highlight recovery.

  • Fourth: #12 AI blur removal and #10 AI super resolution, ex aequo.


Auto White Balance… forget AI - many ( most ) raw files actually have a tag for Auto WB that camera writes regardless of WB settings and yet DxO refuses to read and offer that

Most if not every raw developer uses their own calculations and processing of the white balance…
If one want to compare the intended outcome of the manufacturer, comparing against the in camera jpeg or an export from the raw using the manufacturer raw developing application is needed.

I think DXO should focus on its niche and be the best at that. Meaning image quality and color in RAW photos. I would not like to see DXO become inferior version of programs that are of differnt category, like Luminar Neo, On1, Lightroom etc. Or even photosop. Those tools are different and should be different.

That being said if DXO will add more AI type functionality I would like it to be polished DeepPrimeXD so that it leaves less artifacts in certain situations, make it optimized to be faster with full screen preview and improve on anything else they can about it.

AI that would give basic 2x resize on export using same or similar technology as DeepPrimeXD would be potentially something that can leverage existing technology and give useful increase in resolution.

And if they can add basic ability to use AI for improved repair tool would be nice, but if not, than make current tool more optimized so it can deal with more situations, and faster.

I would be more than happy with that myself. But as added feature to have ability to fill in blank areas after crop would be nice as well, although its possible to do that as it is repair stuff in other apps. I just think that ability to give us utilize maximum field of view for lenses is great if only we could fill in those areas that are blank. That way lens field of view could be maximum.

But just optimizing DeepPrimeXD to maximum in speed and results would be all I need really. Its amazing as it is, but I would think it can get better with current technology and resources that DXO has.



I feel a bit reserved to embrase AI DAM-assistance since it might as well create a mess of our present work. I would never jeopardize all the work I have done for years letting loose a force I’m not in total control of. What might become a mess will not just be the keywords.

Metadata is a lot of work but I don’t want to just cut corners to save time. You can do that a lot using variables smartly instead in a much more controlled way.

There is not a contradiction having both a more irganic control style approach to masking and the precision the new AI masking is offering in LR and CO. We need both. There are ways to achive that in LR and CO too and luminosity based refining of the selections is one way to do it and the new version has been improved there too.

People ought to download a trial before ruling out these new possibilities just as a result of old prejudices. Seeing us believing isn’t it? These new tools are far better than I expected after using them on several different materials a couple of days learning in parallell from some interesting new videos.


… and I’d love to finally see RI database reliability

(really intelligent DB reliability like auto compressed backups, background checking if what’s in the DB is actually on the drive plus means to handle such differences, to name a few)


As an old SQL-DB guy I totally agree. They are not all that in to data integrity yet these RAW-converter manufacturers and that goes for Camera Bits and metadata management tools like PhotoMechanic too which leaves that still up to the user, in a surprisingly high degree.

1 Like

Lightroom has had such features for years. Renaming files, folders and moving things around outside is much less of an issue, Lr simply tags the items and one can then point Lr in the right direction or simply re-sync the archive.

Not really rocket science imo.

1 Like

It sounds as if you are not familiar with competitive products. I don’t know about LR but C1 masks can be refined (made more detailed around hair etc) and feathered. C1’s masking is far superior to DXO.

1 Like

Still manual

Just a comment: Some seem to think the problem is that AI-masking is not enough accurate and others think it’s too accurate and not enough organic and smoth.

Others will always complain about the interfaces of one reason or another. Either because they have changed or just because they haven’t changed enough or in the “right way” - whatever that might be.

Isn’t that very human and pretty typical? :slight_smile: How to really meet these diverging demands as a developer?
Paracetamol or maybe a classic Aspirin?

1 Like

I much prefer manual action in such cases. It’s about what I want to do, not about what some automatic procedure thinks is best for me.

Nevertheless, we could agree on automatic integrity repairs as long as manual override is selectable/possible.

Freedom of choice!

1 Like

It is both. Refinement will always be manual to some extent. Automation is all about productivity and quickly accuire a good starting point. It is a bit like using an auto template at start with a new image in Photolab. That is automation too that has a great potential to improve the starting point when editing. I don’t think the majority want to go back to squre #1 again.

We can well see the developing phase in Photolab as a sort of “refinement” too.

Many users don’t even want to edit their images at all to day. As used to from their phones they expect JPEG-files right out of their camaras to be as ready made as from their phones.In the light of that it’s more important than ever that our RAW-converter gets more efficient and productive.

I have so many images and not enough time. So, I have a lot of images I ought to have developed years ago but I haven’t because my tools like Photolab have been unable to speed up the work and solve that problem through increased productivity. With these new productivity boosting CO tools I think that might come to a change that might marginalize my use of Photolab.


My knowledge of Capture One is not the issue. I quote here @Stenis who said the most important thing:

In the light of that it’s more important than ever that our RAW-converter gets more efficient and productive.

For my use, PhotoLab’s Control lines and U-points are already enough performing for the local adjustments I make. I do not expect a lot of productivity gain in my use with a more performing AI-tool to select objects.

At the opposite, removing the spots of dust on my sensor on every photo is still a manual task totally boring. I dream of an automatic and reliable tool for it. And please, do not troll by saying I just have to clean my sensor before or not change my lens!

Capture One works hard to increase the productivity of professional photographers through numerous improvements, both in terms of UX/UI and features. This fits perfectly with their new subscription model.

What is DxO’s position? Propose the best result OK, but for what type of photographers? Professionals, artists, passionate amateurs, general public?

If the general public is part of the target, then smartphone DNG management should be priority number one.

If professionals are targeted, productivity should be the priority and DxO could focus on original features that their competitors do not offer, and improve existing tools (reliability, UX/UI).

I hope this topic will help DxO collect feedback from Photolab users and their expectations about AI.

1 Like

Maybe configurable is the best :slight_smile: