Denoise AI different result using GPU

Hello all, I realized, that the result of denoising is not so good using GPU with high memory consumption (GeForce GTX 750 Ti) instead using CPU. The calculation is faster but the result is not so homogeneous (seen on sky). Using less GPU memory increases quality, but also raises calculation time to the level of CPU calculation.
Is it a general problem or a problem of specific GPU-cards?

Firstly please go to Help-> Graphics info., press copy and paste the info here.

Then go to Advanced Preferences and press Reset, the next time you update a preview the app will calibrate and use the optimum processing for your PC.

Thanks for the quick response. The calibration I knew and it is not helpful here.

Application & Version: Topaz DeNoise AI Version 2.2.1

Operating System: Windows 10 (10.0)

Graphics Hardware: GeForce GTX 750 Ti/PCIe/SSE2

OpenGL Driver: 3.3.0 NVIDIA 432.00

CPU RAM: 16330 MB

Video RAM: 2048 MB

Preview Limit: 3859 Pixels

Why isn’t it helpful? It will select the optimum processing for your system.

Your vRAM is just the minimum requirement and the driver is out of date.

Thank you for the answer.

Sorry, it means I did it and the result is not as good as the calculation with CPU.

Right, minimum and not below. More vRAM means better and/or faster results?
OK, thats the newest driver Windows found. Thanks for the hint, I will look for a newer.

Don’t use Windows update for NVIDIA drivers, the most up to date can be found on the NVIDIA website.

1 Like

The new driver improved the result. Now there is only a slightly difference to the result by calculation with CPU. For me it’s ok now.
Thank you for the help.

1 Like