Perhaps I’m wrong, but I wouldn’t think that most people need to enlarge images that have been downscaled from the original. Short of tying to turn someone else’s low rez proofs back into something like the originals, I’m not sure why anyone would need to do that. The whole idea of Gigapixel is to enlarge your old archived low rez images, or to blow up your already high quality images to make very large prints.
I know that people here have tried downsizing as a first step, in an attempt to artificially improve the enlargement result, but that may be just the point I was making. They’re adding in the sort of scaling/compression artifacts that Gigapixel has accidentally been trained to remove by teaching it with images that are not the same as the unadulterated images we’re actually trying to deal with.
why limit it to one form of use? That’s not good for business. A good use i find for gigapixel is upscaling textures for CGI, i can go through my entire texture library and upres any 512x512 to 1K or 2K. There are many use cases the sky is the limit. Ideally a smart AI program will be able to detect all use cases and apply different algorithms to get the desired result of the user.
Agreed. In your case the CGI textures are not downsized, just small to start with. You most likely would need a different algorithm than the AI training “mistake” the paper was warning about.
Like you, most of what I’m using it for is taking small dds texture files and enlarging them to at least 2048x2048. The dds format has a unique type of compression artifact that Gigapixel doesn’t anticipate or understand, so I usually have some cleaning up to do.
@andymagee-52287 Let me give you an example of mine. My son and his family live far away so I mainly get to see then on Instagram posts. I do a screen capture of their posted pictures (about 600 x 600px) which include my grandsons and then upscale them in Gigapixel. This is much easier than constantly asking them to send me the original files. Just one use but these are pictures that have been down sized and then I have to up size again.
Interestingly, during my initial testing I downloaded some low resolution stock images from Google images. They were small and fuzzy and had awful compression artifacts, yet when scaled up 4x with Gigapixel, some (not all) of the results were astoundingly good. Convincingly realistic. I surmised that the originals of those must have been included in the AI model training.
Is it normal that processing take more than 5 minute for a 1000x990 pixel JPEG picture?
If yes the software isn’t interesting at all for me.
PS: After finishing I compared the output with the file out of this thread and must say the result of the ‘Photo 2.0’ is horrobil.
The ‘smart enhance (beta)’ is even worse.
For this picture Gigapixel wins.
I can not answer you all question right now but I deactivate the GPU option and scale the image up to 2x its does work. Looks like as soon I choose 3x or 4x times it does crash. The Error message is just saying that the app has been closed due a crash.
input image type and size.6000x4000
preferences you use, e.g. did you press Use Recommended and after that what were the settings saved after calibration. Recommended yes - it did deactivate the GPU support.
then what were the settings you used for processing, and
what parameters did you use when you pressed the Save button
Scale 4x (with 2 its working) face off image type auto
thats all
I am using 5.01. I am also using Lightroom Classic v.9.3 (CC).
If I start in LR and using the “Edit In” option and pics Gigapixel AI, then Gigapixel AI opens, a new copy of my file appears in LR, but Gigapixel won’t actually get the file, so I can up up size it or anything. It is just not doing anything. I uninstalled 5.01 and reinstalled it (and that process is not at all straightforward or clear as there seems to be no file for 5.01, just 4.5 and then an upgrade from there, which frankly seems sloppy to me). How do I get the Upsize from in LR feature to work? It would be the smoothest way and these I could do things to the upsized copy before exporting it with my watermark on it.
Hi,
Thanks for the reply. I am running on Windows 10, so I don’t think that message applies to me but Mac users.
I am pretty sure I didn’t have Gigapixel AI open when I tried to edit from LR. And I did send it a whatever LR has to send over…I don’t exactly get to control that. I think it generally sends a tif file, but I am not 100% sure what it sends over. I’m sure I didn’t send a PSD, though.
After going to through reinstall process, I now have two version of Gigapixel installed on my system. Argh!
2,4 GHz Quad-Core Intel Core i5 // 8 GB 2133 MHz LPDDR3 // Intel Iris Plus Graphics 655
I installed it on my PC as well and its running much better (my PC has a i9 and a 2070 Nvidia card inside)
I have 5.0.1 installed (and I had it before coming here today, too). I was referring to the other comment about needing to open LR first…I don’t see any comment about that in the opening post, except something for Mac users.
I am not sending PSDs to Gigapixel. I have sent several hundred pixels through it and to other apps I have installed. I have no problems with DeNoise AI or Sharpen AI. I load in CR2 & CR3s in LR, so I don’t see where a PSD would get into my workflow. That is not the issue.