Video Enhance AI v1.2.1 - OpenVino V3 and Bug Fixes

this is the xml friendly view:
System

|||- Provider

[ Name ] ESENT|
| — | — |

|||- EventID 455

[ Qualifiers ] 0|
| — | — |

Level 2

Task 3

Keywords 0x80000000000000

|||- TimeCreated

[ SystemTime ] 2020-04-24T13:37:35.260876500Z|
| — | — |

EventRecordID 21262

Channel Application

Computer DESKTOP-VAL58TU

Security

- EventData

svchost

22288,R,98

TILEREPOSITORYS-1-5-18:

C:\WINDOWS\system32\config\systemprofile\AppData\Local\TileDataLayer\Database\EDB.log

-1023 (0xfffffc01)

That would be good and maybe could speed up the rendering process knowing Windows squeeze something like 2GB of your GPU Memory.

So far it is working pretty well for me, apart from a few small bugs. Where can I report them ?

Also, it would be fabulous to have a “pause” option if this is possible. for some videos, the processing time is quite long, and sometime, I’d like to stop the process, to be able to resume it later (after a computer reboot for updating other apps for example).

Cheers !

4 Likes

I know, I am currently using Windows, but Linux would be more convienient because Windows is not my main os.

That would be great!

I am a new user and enjoying the software so far - realizing very quickly that the render times make certain projects I was hoping to use if for a little…intimidating? I think it would be great if Topaz (or others here with deeper experience with the program) would post a true recommended “Best, Better, Good, Minimum” set of system specs for achieving better render times on projects. What type of dedicated render machines is Topaz using for their online service for example? Is the CPU option designed to work best with specific chipsets/# of cores, is the GPU option significantly improved by moving from a 1080 to a 2080 - what about specific editions of cards - OC, ROGG etc.? What are the actual render time differences using OpenVino? If I wanted to build a decent dedicated render box for basically just using VEAI and upscaling my old SD projects - what components/configuration would Topaz recommend? Sorry if I missed this information somewhere else. Again - fascinating software - really getting some nice results on my (short by necessity) initial experiments…Hope someone has suggestions! Thanks again!

Hi,

Could you guys at least add “lossless” option on the output file? so we can encode later without own encoder of choice. I think this is very important!!! Quality loss from such awesome software is a pity…

this software is madness I love it!

Raise a support request at the main website…

I’m getting this weird random blue blob when enhancing, this happens with the Gaia-HQ profile.

blue blob example pic 1
blue blob example pic 2

2 Likes

Don’t understand all the love for Gaia-CG. In all of my testing Artemis-MQ gave better results every time.

1 Like

I think I found a fix for crashes with RTX cards:

In the log I found out, that the cudnn couldn’t be initialized properly so:

I installed visual studio 2019 community
cuda toolkit 10.1 update 2
and the cdnn 10.1 release.
the cdnn has a special way of installing.
The installation has a proper order. Check below.
I also restarted after, don’t forget to do that.

There is a video on youtube on how to install it:
Deep Learning Tutorial #2 - How to Install CUDA 10+ and cuDNN library on Windows 10

Hello,

Mac user here. Been stuck on 1.1.0 because every version I install afterwards simply won’t open at all, including 1.2.1. I’m not sure why this is happening. At first I thought it was a fluke and 1.1.1 was just buggy and I gave it a pass since I still had 1.1.0, but now it’s been a few updates and I just can’t get the program to run.

Using an iMac 2019 with a 8-core Intel i9 and an AMD Vega 48 (even thought I know the AMD GPU doesn’t do anything here). Don’t know where else to turn.

EDIT: I should mention I’m on Mojave 10.14.6

I’m also having frequent crashes with a 2080.

Check Out the fix that I posted yesterday. It involves cuda drivers

Works fine on iMac i7 2017 with Mojave.

1 Like

I have the same problem with 2700x and 2070 Super. 1.2 doesn’t work. The solution is roll back to 1.1.

1.2.1 crashed after 6 hours upscaling by i9-9900s + Nvidia2070s + 64G ram + windows10x64, I have no way other than rolling back to 1.1.0, again …

What options did you check for installation from the component install list?

In installed the community one.