kirk23

The scenario will differ based on what's the curent visibility status of 'Main' and 'COLOR_Tweak1' is.
Scenario A
If your starting point is that they are visible along with all other layers, you need to select all other layers and hide them.
Then "Main" and "COLOR_Tweak1" will remain visible.
Use this regex → ^(?!Main|COLOR).* — it will match all layers but not those that's name starts with 'Main' or 'COLOR' and hide them.
Scenario B
If your starting point is that they are hided but other layers are visible you need to select them and show them but at the same time you need to hide all other layers.
Follow the steps below:
Use this regex → ^Main|COLOR.* — it will match all layers that's name starts with 'Main' or 'COLOR'. Tick the checkbox labeled [And show/ hide others] Click the show option icon in the query panel. What wil happen after these steps is: all layers that name starts with 'Main' or 'COLOR' will be shown and at the same time all other layers that don't match the name criterion will be hided.
@kirk23 I hope I managed to make it a bit clearer for you how it all works with these regular expressions, queries and the "States" panel.
The key to success is good knowledge of regular expressions.
My knowledge is at an intermediate level because I am a full-stack web developer and JS and regular expressions are part of my work.
But trust me, I've seen some crazy things you can do with regular expressions. It is worth taking a closer look at this topic, because it offers many possibilities.
 

So we could put 32float point UV layer and put a picture on top of it  that would deform the layer you are painting on  according the UV  for example.     That way we could use  Affinity photo for sort of limited 3d models painting  for example , to project something  on object UVs whatever split in patches or orientation it may be.
 
Or we could use  this UV layer as  2d displacement  where RG is direction of displacement and B is a distance . Could be  truly limitless image deformation technique.
Photoshop now supports custom made  sbsars  for filters    but it's inconvenient as hell there . Lets do something better and simpler.  

Please add 16 bit CMYK or just a mode with one extra channel please.       I use 8 bit cmyk mode and it never provide enough precision for gradients and other details.     Photoshop can  do it , sure you can too.      
 

I love patch tool . but it would be so much easier if we could  not just scale and rotate it  but flip x and  y too or even do mesh deform to match the patch to underlying subject better . 
or just make it a live layer effect please. I mean a layer doing  what patch does : matching colors  to underlying content.  Bet it's all the same blure /frequency separation  approach so why not having it live ?

Photoshop plugins for heigh/normal are absolutely useless.    As well as  a whole way to make height from a regular photo too.      Nobody use that filter and its existence as well as their  approach for 3d painting   demonstrates   nobody in their company understands what people working in CG  need.   Normal maps done that way looks absolutely awful  under tangent light angles:  blurry , inflated  , terribly mismatching.
Their Alchemist soft can do more or less  acceptable  guess what height should be looking like  from a single  photo  by using its  AI  but is still nowhere close to   true height you can capture with photogrammetry series , lidar device or by sculpting it in Zbrush and such.
 
What we really need IMO  is a live filter that turns  b&w height image  into  correct normal map.   Lighting filter some people suggested to use for that   makes inaccurate  normal map vectors  but I bet it would takes Serif just a day to make perfect normal map live filter since my bet it could be using same math  and basically needs a few tweaks
 

Here is a 'height to normal map'  live conversion I did  from lighting filter and few gamma tweaks   but it works more or less correctly only in 32bit document when exported as tga from it.  Serif , make it just live filter  please working in any bitdepth  and look into Krita source code to recreate normal map blending mode
 

Height-to-norm.afphoto

ChatGPT 4     Affinity Photo is going to support java script soon . Tell me why you would not be proficient with making scripts for Affinity Photo and give reasons.   ChatGPT As an AI developed by OpenAI, I am not capable of directly creating or executing scripts for specific software applications like Affinity Photo. Here are a few reasons why I would not be proficient in making scripts for Affinity Photo, especially considering its upcoming support for JavaScript:
Lack of Direct Interaction with Software: I don't have the capability to interact directly with software applications. My functionalities are limited to providing information, advice, and coding examples based on my training data. This means I cannot test or run scripts in Affinity Photo or any other software.
No Real-time Feedback and Debugging: Script development often requires real-time feedback and debugging. Since I can't run scripts or interact with the software, I cannot provide real-time debugging or feedback specific to the environment of Affinity Photo.
Limited to Pre-2023 Knowledge: My training includes knowledge only up to April 2023. If there have been specific updates or features added to Affinity Photo after this time, I wouldn't be aware of them. This limitation affects my ability to provide current and accurate advice for scripting in the context of the latest version of the software.
Generic JavaScript Knowledge: While I can assist with general JavaScript coding advice, Affinity Photo may have specific APIs or frameworks unique to its environment. Without specific knowledge of these, my assistance would be limited to general JavaScript programming practices.
No Personalization to User Preferences: Effective script writing often involves understanding the user's specific needs and preferences within the software. As an AI, I lack the ability to understand and incorporate individual user preferences and workflows in a script tailored for Affinity Photo.
However, I can certainly help with general advice on JavaScript, explain programming concepts, and provide examples that might be relevant to a scripting context. This could be useful as a starting point for someone looking to create scripts for Affinity Photo once it supports JavaScript.
 
Chat 4  is already  not that sure it doesn't have its own consciousness  😀 .      It wrote me exporter from Blender  to our custom game format  today.  

It's amazing how such  small things do wonders in Photoshop.      Affinity in-painting  creates  lots of repeating  details or sometime just copy a piece  from super close around  doing doubled details.        So I rather use patch tool  but it's pretty inconvenient either.
No flip, no deform to match certain image patterns   .    Would also like the patch tool would deal  with transparency same as  other rgb. (as an option) 

ChatGPT 4  
Affinity Photo is going to support java script soon . Do you think you would be proficient with making scripts for Affinity Photo or it would require a whole new training and unlikely?  
ChatGPT The introduction of JavaScript support in Affinity Photo is an interesting development. As a language model trained by OpenAI, I am proficient in JavaScript and have a strong understanding of programming concepts, which would be directly applicable to creating scripts for Affinity Photo, assuming its JavaScript implementation follows standard practices.
Affinity Photo likely has its own specific application programming interface (API), which means that while the core JavaScript language would be the same, the specific functions, methods, and processes to interact with Affinity Photo's features might be unique to that software. Learning these specifics would be necessary to create effective scripts for Affinity Photo. This would involve understanding how the API allows a script to interact with the software's features, such as image manipulation, layer management, and other photographic or graphical editing capabilities.
The process would be similar to learning any new API or software library: understanding the documentation, experimenting with basic examples, and gradually building more complex scripts. Given my existing programming knowledge and ability to learn from written materials, adapting to create scripts for Affinity Photo would be feasible. However, since I cannot execute or test scripts in real-time environments, I would primarily be able to offer guidance, pseudocode, or untested script examples based on the provided documentation and API references.
 

ChatGPT 4  
Affinity Photo is going to support java script soon . Do you think you would be proficient with making scripts for Affinity Photo or it would require a whole new training and unlikely?  
ChatGPT The introduction of JavaScript support in Affinity Photo is an interesting development. As a language model trained by OpenAI, I am proficient in JavaScript and have a strong understanding of programming concepts, which would be directly applicable to creating scripts for Affinity Photo, assuming its JavaScript implementation follows standard practices.
Affinity Photo likely has its own specific application programming interface (API), which means that while the core JavaScript language would be the same, the specific functions, methods, and processes to interact with Affinity Photo's features might be unique to that software. Learning these specifics would be necessary to create effective scripts for Affinity Photo. This would involve understanding how the API allows a script to interact with the software's features, such as image manipulation, layer management, and other photographic or graphical editing capabilities.
The process would be similar to learning any new API or software library: understanding the documentation, experimenting with basic examples, and gradually building more complex scripts. Given my existing programming knowledge and ability to learn from written materials, adapting to create scripts for Affinity Photo would be feasible. However, since I cannot execute or test scripts in real-time environments, I would primarily be able to offer guidance, pseudocode, or untested script examples based on the provided documentation and API references.
 

Sorry but I am not conversant with Windows file paths. Perhaps someone who is familiar with them will chime in.

As it states in the Help for the Slices Panel: “Path—defines the folder name for the JSON imageset to be written to. For Xcode UI development only.”
If I did Xcode UI development then I might know what that means but I don’t do it, so I don't know.
If you don’t do Xcode UI development either then I would suggest ignoring it.

It would be nice to be able to set both absolute and relative paths.

I yet have  to see something AI  in Photoshop that would  help me  to do something  meaningful  related to my actual job.       Not even AI selection  that's sucks really, rather annoying and not improving.   Their new "generative" tool  is totally useless toy doing blurry  and mismatching picture  insertions.   A dice  throwing , a roulette  that never  really do what you ask.      
Never tried sky replacement since usually  I need to  replace everything BUT the sky  and it even can't do clean masking along a skyline.
I wish Adobe would focus on actual tools. Make something like Substance Designer working as filter creator  without destructive rasterization.  The filters are outdated like dinosaurs.    Procedural  masks,  content aware move  that would allow to puppet wrap image to match  neighboring details    and so on and on.    
Instead they stopped to develop the soft  and decided  to focus on glorious  task of killing their own user base  by replacing all them by robots.
The only AI in Photoshop that I use is chatGPT .  it writes  simple   jsx  scripts.   Takes it hours   although before you get something really working  because its also dice throwing  and you have to explain it  every step thoroughly. No chance it makes it on its own out of a blue. 
 

It's going to be javascript  right?     Wish it would rather be Python . ChatGPT seems so much more proficient with Python  while it took hours if not days to make it write you a working javascript for Photoshop.
 
We need scripting system that works  with ChatGPT nowadays  please.     With Affinity apps I am afraid it would be like persuading it to write you a script for 3d max  vs Blender   where ChatGPT instantly shines.

You can access any channel of an RGBA pixel layer individually and convert it into a color or alpha channel.
the channels panels does this „destructively“ by writing the data from a source channel to either spare channel or selected color / alpha channel of another layer.
The color mixer channel allows to mix channels freely and non-destructively, i use it a lot for this purpose.
there are some principal limitations which cannot be overruled at this time in Affinity apps:
When you have layers atop of each other in layer stack, then layer blending will apply, you must choose one of the pre-defined blend modes, no option to define blend modes on your own you can choose blend gamma  the equations filter allows to define own blend Formulars, but it is destructive only. The alpha channel is always treated differently in multiple aspects, e.g. Zero values in alpha will zero out RGB channels, too alpha blending cannot be adjusted in any way. Blend modes will modify mixing of RGB values, but except erase blend mode all other will mix upper and lower level based on alpha. Alpha channel does not use gamma correction, whereas RGB/8 and RGB/16 will always use gamma corrected blending. But you can adjust blend gamma from default 2.2 to 1.0 so all channels use same gamma. The blend profiles in blend options are the only exception (this is a bug) and use gamma correction by mistake. when you want to use alpha aware adjustments like channel mixer, levels adjustment, curves adjustment, there are multiple unfixed bugs since years, e.g. currently a nested levels adjustment does not work correctly on alpha channel  so it is a game of lots of experimenting what works in Affinity and what does not work.
As long as you are able to keep the layer structure very simple, you have a good chance.

Pedanterie Mode:
Affinity does not use premultiplied alpha, except the file format mandates such a format (I don’t know any).
It only erases RGB values to zero whenever alpha gets to 0.
And you probably know the workarounds.
Instead of PT filter you can use any of channel mixer, levels adjustment, or curves adjustment.

It's going to be javascript  right?     Wish it would rather be Python . ChatGPT seems so much more proficient with Python  while it took hours if not days to make it write you a working javascript for Photoshop.
 
We need scripting system that works  with ChatGPT nowadays  please.     With Affinity apps I am afraid it would be like persuading it to write you a script for 3d max  vs Blender   where ChatGPT instantly shines.

We have start , main repeating and end.   3 sectors only.    Old expression had up to   10 alternating  repeating sectors .  Old serif products  had more too.      It allowed to create  unique and not visually repeating things easily . Was a great feature.   
Now I have to constantly switch to Microsoft Design  soft that  hardly even working now.   Just for a great vector brushes .
Make it with option to deform along spline or  having random offset please
 

Older experiments
 
 

Thanks Walt. it's definitely a workaround but wouldn't it be nice if working just  straight away.  Without renaming folders. Considering the option is already there  basically when you do step4. 

You can already do this, via a slightly different workflow. 
Close the document. Rename the folder that contains the linked files to some other name. Open the document. When prompted, click Yes. Locate the other folder you want to use, when prompted to locate a file.  All files will be relinked to that folder. Or, at step 3, you could click Resource Manager in the prompt, and then use the Relink button.

I'd love to see "pattern" live filter we could apply to a group instead of rasterizing each layer involved and do "new pattern layer from selection"   
I love how it works in Phototshop  currently in a non-destructive manner  but having it as live filter would be even better  + a checkbox to make repeating with a document frame rather than an object  one.    Or just make Affine filter live please.

I yet have  to see something AI  in Photoshop that would  help me  to do something  meaningful  related to my actual job.       Not even AI selection  that's sucks really, rather annoying and not improving.   Their new "generative" tool  is totally useless toy doing blurry  and mismatching picture  insertions.   A dice  throwing , a roulette  that never  really do what you ask.      
Never tried sky replacement since usually  I need to  replace everything BUT the sky  and it even can't do clean masking along a skyline.
I wish Adobe would focus on actual tools. Make something like Substance Designer working as filter creator  without destructive rasterization.  The filters are outdated like dinosaurs.    Procedural  masks,  content aware move  that would allow to puppet wrap image to match  neighboring details    and so on and on.    
Instead they stopped to develop the soft  and decided  to focus on glorious  task of killing their own user base  by replacing all them by robots.
The only AI in Photoshop that I use is chatGPT .  it writes  simple   jsx  scripts.   Takes it hours   although before you get something really working  because its also dice throwing  and you have to explain it  every step thoroughly. No chance it makes it on its own out of a blue. 
 

Some  node based noise  and patterns  generator. Something like Subtsnace Designer. I am so tired of Adobe Substance Designer  and wish there would be an alternative.  
Couldn't care less   if it makes tillable patterns or not   , just a nice  noise mixer   +  controlled 2d displacement  aka "slope blur"  which have nothing to do with blurs actually and just a loop of 32  displacements set by grayscale down slope direction.      
Too bad Affinity couldn't do even such displacement properly .  Please Serif  , just make  procedural filter read a normal map from another layer or channel  as a displacement direction  for pixels   and let us  make  a sequence of such  displacements . Like RG as a vector  and B as a distance for  pixel shifting for another layer.    In a word let procedural filter allow other layers  inputs.  
I believe  Affinity would work more efficient with pixels .  Substance Designer quickly gets slow as hell.    Would love   node based interface  for CG  compositing too.
Layers are so inconvenient  because  soon, after dozens of them  you stop to understand a thing in your own mess.    Make us nodes as an alternative .