kirk23
-
Posts
721 -
Joined
-
Last visited
Posts posted by kirk23
-
-
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)
-
Adobe recently added flip options for their content aware move tool . Please Serif add flip and mesh deform options to patch tool . So we could adjust something to existing details with mesh deform option before applying the patch.
Also would be super helpful if the patch tool would work in alpha same way it does in rgb. As transparency would be just one more channel to patch.
-
13 minutes ago, chessboard said:
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 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.ChatGPTAs 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.
-
-
Would be nice to have a live filter that would match every rgb or A(as an option) value of pixels to what's beneath . So getting sort of automatic color and tone adjustment for a new layer to be mixing seamlessly with background.
it's like when you do frequency separation and get hi and low frequiency layers the low freq layer is actually blurred (with a slider) background.
Might be several other approaches too but all based on blur and frequency separation. Perfectly doable but require so tedious routine and complicates the stack so much I would love just a live filter doing so.
Or just let us do our own live filters by letting procedural filter see beneath. Please 🙏
-
I doin't care about cmyk and publishing , just need one more extra channel . Can do it in Photoshop but cant here. Your layer system and layer linkin is already way more convenient than Photoshop one. It would be just another step. I am pretty sure it shouldn't be much of a problem.
-
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.
- loukash and chessboard
-
2
-
i am om
27 minutes ago, Old Bruce said:Ignore Xcode (Apple's Mac programming suite of software). Xcode is not needed for this to work.
Make a document. Draw a shape on it. Go to the Export Persona. Export something to somewhere on your computer. Now click in the Path area and write MyNewFolder/ (slash included) Export again. Look in the Finder for the original location (somewhere) and check to see if now there is a folder called MyNewFolder with the slice in it.
I am on Windows and this is not working.
it doesn't let you put the slash there and writes opposite slash instead.
-
10 minutes ago, chessboard said:
I assume that chatGPT generates Blender scripts quite well because there are many references on the web that chatgpt has "learned" from, due to the open source nature of Blender and therefore a large number of users who know how to script and share their scripts on the web.
Similar knowledge cannot be expected for affintiy scripts, as chatGPT does not learn to script. It does not "know" anything about scripting logic and scripting languages, nor does it understand how to read API documentation and combine this information with knowledge of the rules of a particular scripting language. It simply can't think. Instead, it simply collects scripts that others with knowledge of the scripting language have already written and can combine them into new scripts. This works all the better the more often the tasks set have already been solved and published on the web. If you ask chatGPT to create a script for a very specific and unique purpose, it is more likely to fail.
Scripting in Affinity will be so new that chatGPT will not immediately find enough scripting input. If scripting in Affinity becomes popular, the later versions of chatGPT will probably also be able to generate scripts for the Affinty applications. It is not a question of which scripting language is used. There just needs to be enough sample material available.
It's might be true but much to my surprise ChatGPT4 actually suggests ideas how to solve things if something doesn't work. I subscribed for a month and see the difference . Looks a bit like thinking actually. It's just pretty tiresome to check its ideas since only one from 10 works . It did me a few nice Photoshop scripts I couldn't do myself . But it took me a whole weekend. More approaches it did to workaround something slower it starts to work , up to so slow you wait half an hour for each new piece of code . And if the code still doesn't work it starts to do useless detours and back rounds and you constantly need to focus it on exact task.
-
6 minutes ago, Old Bruce said:
It is quite unintuitive. There is the main file path which would be the folder the slices would be saved to. The Path adds to that path. For example if I am saving most files to /Users/<YOUR_NAME_GOES_HERE>/Downloads/ and then I use the Path to try and save to /Users/YOUR_NAME_GOES_HERE/Desktop/MySlices/TIFFs/ then I will wind up with my TIFFs being saved to /Users/<YOUR_NAME_GOES_HERE>/Downloads/Users/YOUR_NAME_GOES_HERE/Desktop/MySlices/TIFFs/ the red bit will be created folders in my Downloads folder. I would have to set the basic path to Desktop in order to have the slices saved to MySlices/TIFFs/
The first time I run this I can have the folders MySlices and TIFFs created, subsequent exports will just use the already created folders.
I would love for it to use the Actual complete path I want instead of creating a new path but such is life.
It implies we still can use this path option somehow? For me it never worked at all. Is it working on apple only ? I googled Xcode and it's something apple related ?
-
And it would be nice if export persona could have access to "States" in Affinity Photo and could export selected states for each slice. With option to add state name as a file suffix . Like slice "button" would export two states "on" and "off" like button_on.tga and button_off.tga
BTW. does anyone know what "path" field for in slices pane? Whenever I tried to input a path there it ignores it
-
I need scripting I could use chatGPT4 for . Not just any scripting. So far Chat GPT is good for writing python scripts for Blender . Not sure it's open source nature or it have just been trained well on Blender but it's where it actually works.
Persuading it to write you 3d max script is its own challenge for example . For photoshop it may take days with miss and hit before Chat would write you java script that actually works.
So please do something ChatGPT would proficient with. Not another " Thank you for buying our product. Now kindly hire a programmer"
-
it's not
9 hours ago, fde101 said:There is evidently a Blender plugin for sbsar files that relies on a component called Substace Automation Toolkit to be installed, but when that is available, is able to render sbsar files directly within Blender: https://xolotlstudio.gumroad.com/l/stxJi
It might be possible to take a similar approach with the Affinity products to gain access to these files if it is something you have a use case for - if Serif does not provide this, perhaps as a plugin once the SDK is available?
It's not actually what I meant . 3dmax have a substance plugin too for example but it's just a way to bypass exporting bitmaps and loading bitmap textures. And too much of a complicated extra headache to be useful.
Not exactly a "filter". I mean something we could input one or two images and produce new result on the fly . If it could read affinity layers as inputs then it a whole new story.
-
Soon Photoshop will get its best and most amazing update for years probably : sbsar files as procedural filters. The ones we could export from Substance designer and do whatever filters we would like . Not live ones unfortunately
Wish Affinity would have something like that. Doubt it could ever read sbsar files . Adobe would never allow it but I wish we could have our own procedural filter to read " bellow " at least like some other filters or better any specific layer and has as an option a simple node based interface . Something I could use my 16gb gf3080 for .
-
-
12 hours ago, NotMyFault said:
It only erases RGB values to zero whenever alpha gets to 0.
Thank you NotMyFault. I didn't know about background trick but it still doesn't help me much since I want tga or tiff or exr as linked image from which I could have an access to each individual channel to use them for masking . Like 4 masks from cryptomatte I packed in one RGBA output file in Blender compositing to be then accessible in Affinity with procedural filter. Do you know a trick how to do it with PF so we could use same linked image as a masks source without doing black holes in RGB ?
Works with 3 masks packed perfectly well but the alpha one spoils it .
-
I often need to work with tga files and Affinty always mess them at open stage doing black wholes in RGB channels where Alpha is zero.
When you save tga there is at least an option to add to alpha some 0.0001 with procedural filter that lets to avoid it but when yu open the file it's inevitable. Can we have an option in the settings somewhere to NOT doing this please.
-
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.
- PaulEC and chessboard
-
2
-
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
-
9 hours ago, NotMyFault said:
Older experiments
Yeah. but practical implementation is a key. Could be just extra channel without any crazy tricks . Simple and easy. Corel painter have a perfect floating point depth channel for example. They had it since ancient times but never let you do anything meaningful with it except impasto.
The soft needs so little modification really to be a perfect 2,5d Zbrush replacement.
-
Would love if Affinity have a mode with one more channel dedicated to depth /height. Like some painting apps, art rage, corel painter etc. Which use it mostly for impasto simulation and canvas textures.
Could be a whole new version of Zbrush 2,5d mode but rather non-destructive with true layer support .
All it needs is just depth /height channel in brush dabs , an extra alpha in tiff images maybe and a few specific blending modes.
Depth combine blending where if pixels of layer 2 are higher then layer 1 they are visible and other way around masked . Basically (layer1 max layer2 )- layer1 and some levels based threshold on top of it or perhaps just classic and simple if else binary masking way.
And another blending mode where same if else pixel selection blurs layer 1 and add depth of layer 2 on top of it.
Would work nicely for all sort of bokeh imitation and for doing some special depth based displacement and filters. Isometric phone games mockups , materials for CG and so on and on without super complicated layer stack where you couldn't recollect and figure out anything just next morning .
t
-
3 hours ago, walt.farrell said:
You can already do this, via a slightly different workflow.
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.
-
Please make it possible to input new path to selected resources. I use Affinity photo to composite 3d render and sometimes I need just to relink the same names files but to a new folder . Please make Replace button work with several resources selected to be able to point to new folder for all of them or just let us copy paste the new path for all selected at once.
-
All it requires is just having 5 symbols. One for the document itself and extra 4 for sides. Can Affinity do it automatically please and make a full screen preview mode so we could estimate how repeating details look . Maybe just a hot key to on and off. While I can do symbols in Designer on my own it's hard to manage them and easy to accidentally shift and mess . Would be nice to have just one click "pattern" mode. Maybe in Designer but better in both .
-
Something we could write our own formula . Would replace a lot of complication in layer stacks
Rasterize automatically
in Feedback for the Affinity V2 Suite of Products
Posted
I support Image stay image by default. Find it quite convenient . It helps to keep everything non-destructive and resolution independent. Saves you from dealing with annoying "smart objects" you waste your time for in Photoshop.
The only thing I am missing is ability to link pixel content to another layer . i.e make a sort of live rasterization. Especially since such thing is already happening for a screen.