Gigapixel v5.6.1

Hey Paul,

Tech_One9 would be great!

Thank You

Randy

1 Like

Looks like support finally got round to it for you!

Hey Hey, looks like you are correct my friend. Thanks again!!

Randy

Interesting and good to know, thank you. What version of the Nvidia drivers do you use, please?
The Game Ready drivers or the Studio drivers?

If they are okay the Studio drivers.

10 posts were merged into an existing topic: Gigapixel v5.4.5

Tested gigapixel 5.6.1 and it completely washes out the colors out of any picture i attempt to upscale, i’ve tested the following:

  1. Re Install gigapixel (FULL INSTALLER)
  2. Update to latest nvidia driver.
  3. Render using CPU Only
  4. Render using GPU Only
  5. Disable / Enable “Apply Raw Color Correction” No difference using on/off
  6. Disable / Enable " Apply Auto Lens Correction" No diffence regarding colors
  7. Tried multiple image formats, png, jpg, bmp all end up the same.
  8. Enable / Disable “Reduce Color Bleed” No difference between the two.
  9. Enable / Disable “Face Refinement” No difference between the two.
  10. Attempted upscale using all different models, “Standard, Lines, Art & CG, Low Resolution, Very Compressed” all end up with exact same washed out colors.
  11. Uninstalled DeNoise AI Completely just to make sure it wasn’t doing anything anyway, still same washed out colors

Look at the result below, in the preview window the colors seem fine, but whenver they are rendered out the colors are all washed out with a “green/darkish” tint to them.

https://i.imgur.com/4EilGY4.png

God damnit topaz, just trying to figure out how to open a support ticket is impossible now, i click support and all i get is some useless FAQ page and no way to actually write a ticket, why are you doing this to people? Why is everything so god damn convoluted?

Anyway, above is my problem, i couldn’t figure out how to open a support ticket so i guess this open thread is now my support ticket.

Here is the support site: Topaz Labs

I noticed the “contact us” button is not working but it is the weekend so maybe you can try it on Monday.

Zamfir said that the CPU was slower but made sharper images. I ran a quick test and my CPU produced a sharper image than my RX 5600 XT GPU. However, the GPU did sharpen compared to the original. For most cases I would still choose using a GPU because of the extra speed.

Why would there be a difference in result quality between using the GPU vs. the CPU?

1 Like

EDIT: Upon further investigation my comments are incorrect, Gigapixel AI does display the original image. It is indeed a windows photo viewer which enhances images when zoomed in.

Can you please remove the artificial reduction in quality for the preview of the original images?

While there is doubt that Gigapixel does an excellent job at upscaling, the comparison mode between the “original” image and the upscaled image is highly misleading.

Below are three random images that I grabbed off google.
The left image is the original image viewed in Windows photo editor.
The middle image is the “original image” preview in Gixapixel.
Right is the upscaled image.

It should be pretty obvious to most people that there is a significant reduction in quality between the left image and the middle image.

1 Like

Has there been any word on when Gigapixel is getting macOS Monterey support?

There is no reduction of quality in that sense, because by enlarging the artifacts are simply enlarged.

To my eyes, the Windows previews look washed out while the gigapixel images show hard compression edges.

Which is correct in the sense that it can handle it afterwards.

I remember this was always an issue more or less because to make the preview in the output quality it would have to process the whole image which would take the same amount of time than processing the image. So to speed up the preview the quality has been lowered…

There is a thread pinned at the top of this forum, you can’t miss it:

https://community.topazlabs.com/t/contacting-support/25804/5

For most applications in which presentation quality matters, Bilinear or Bicubic scaling is used when enlarging. Gigapixel uses the Nearest Neighbor algorithm instead which is more useful for production purposes as it shows the original pixels as clearly as possible.

1 Like

Thanks for the responses @Viscerous and @TPX. Upon further investigation, I have learned that when viewing a low-resolution image, many programs (including windows photo viewer) use algorithms to “improve” image quality when upscaling the image. The image displayed in the Gigapixel AI is indeed the original image.

I will make an amendment to my original comment.

A wish for a future Gigapixel version down the line:

Possibility to upload own, relevant pictures to use as reference!

For instance: I have taken a blurry image of, say a loudspeaker, using my phone camera in poor lighting.

In Gigapixel, I upload several razor sharp images of said loudspeaker, from manufacturer’s commercial image bank, as references.

Gigapixels puts together a sharp image of my loudspeaker, using the other images as reference.

1 Like

Can you post this Gigapixel AI idea here:

https://community.topazlabs.com/c/topaz-products/product-feature-requests