is there a link to the fix? I don’t see one
| AiDon Don Beta Tester
February 8 |
- | - |
Have a look at this report on the forum where AMD GPUs were having was having issues with Photo AI and the OP downloaded a fix from AMD forums …
Click on the blue link in that post above … (not here)
Yes, it’s a completely free AI software. You can use Automatic1111. The interface is rather complicated. I find it rather complicated (it uses SD 1.5, 2.0 and SDXL models) or Fooocus (a more simplified interface, but it only uses SDXL models) or other packages from the Stable Diffision group. Like RuinedFooocus. It looks a bit like basic Fooocus. And uses only SDXL models. There’s also ComfyUI. This one is entirely nodal. Ideal for those who like working with nodes. It uses models from SD 1.5 to SDXL.
For your information, SD 1.5 has resolutions from 512x512 to 768x768 maximum.
For SDXL, it goes up to 1024x1024, but for 4/3 and other formats, it can go up to resolutions of 1152x896. After that, the generated image can be scaled.
To easily install a package, you can use the Stability Matrix launcher.
Here are the packages available in the launcher
You can also create your own templates via one of the 2 packs in this section here
1 Like
Have you tried removing everything to make a clean installation? Afterwards, I saw that you were on MacOS. I’m on Windows. So the problem doesn’t even arise.
Maybe in your case, there are a few obsolete files causing errors. That’s just a hypothesis.
Yes, I removed all files, including those in hidden directories.
I started repairing the access rights and nothing was broken.
Then I reinstalled and checked the newly created files. They were all current.
What else should I do? And then the all-important question: Why does the standalone version run without any problems and when it has been started once, calling it up from Photoshop also works without any problems?
@anthony.lawn @yazi.saradest Creating Camera Profiles Using a Color Checker.Sample uploaded Notice How Camera Profiles are made All using different software.
IMG_0260.DNG (18.0 MB)
IMG_0398.DNG (16.3 MB)
IMG_0399.DNG (22.3 MB)
IMG_0400.DNG (16.6 MB)
Thanks for this info! I’ve got SD installed on my Mac locally, the geeky way (where you get it going via Terminal but use the browser for GUI) but also use the free DiffusionBee app, which was just updated. It is one of MANY apps to easily get one going in SD AI.
AI getting Photo AI’d:
Then artsified:
2 Likes
Thx so much for the details! That helps a lot to know how to navigate it.
I see. Well, in that case, I don’t have a workaround at the moment. Sorry
You’re welcome. I’ve heard of DiffusionBee. But never used it. Note that it would be interesting to have a launcher similar to Windows but for MacOS.
AI photo upscales by AI photo gives a digital painting look.
You’re welcome 
.
1 Like
Hi, I’ve managed to improve your image considerably.
It’s not 100% perfect, but I made 3 passes in Photo AI with 3 different settings. I then imported the 3 images into Photoshop and, using masks, I painted out the areas I wanted to remove and kept only the interesting ones. Next, I imported into “Fooocus AI” (a pack from Stable Diffusion A1111) and opted to do a variation of the photo. Once happy after 4-5 generations, I imported into Photoshop and kept only the original face and chest pattern. As a result, I was able to refine the photo and remove 95° of the image’s artifacts.
Note the quality of the details in the hair
2 Likes
I’m sorry to hear about your problem. If it were me, I would go get the computer if it is accessible and the house seems stable for now. I hope things get better soon.
1 Like
I don’t have the latest version of PAI so for fun I ran your result through Luminar NEO with a 2X upscale and then Super sharp with face enhance. I did it once and here is the result.
1 Like
But the problem is that my restoration was 4 times the resolution you upscaled. I don’t know why the photo was reduced in resolution by 4 when I imported it.
Next time, I’ll use an image link because I have the impression that the site has a size limit for image resolution when importing.
Ici, ma mise à l’échelle est encore meilleure. J’aurais dû réduire la résolution de 4 et l’augmenter de 6 par la suite.
Now everything is perfectly sharp without too much exaggeration.
True about the PAI painting look, but my last example was further artsified with Exposure’s Snap Art 4.
1 Like
I Just Downloaded The I Mac Version.
I too am getting the freezing on face detection. I have 2 computers. This one is a newish computer, but with no real GPU. So it uses the computer’s power to work. So naturally it is slow. Which I fine. Some photos it works fine with face detection. Others it fails all the time.
I am running 1.3.6 on my machine machine which has a proper GPU with 6gb of ram and is quick. I keep the old version on there because I find it works better for most of the photo. Mainly because anything newer tends to detect with lens blur model and the sharpening with that model makes my photos look like crap. The standard or strong model look better. But with 2.3.2 when if it decides to use lens blur and I manually override to use standard, I get these squares around the subject in the background. I have subject detection turned off. Also as mentioned in an earlier post, in some photos it randomly changes the color of a hat. The hat is all black, but after PAI runs, it shows up partially gray in weird patterns
