Why would a poor quality source video blow out a system instead of just producing a poor quality enhancement?
Poor quality power supply.
I can no longer roll back, because the version 6.0 and beyond installed some junk into the OS, and now it will not accept the earlier software as something it can validate. So, I am totally screwed by Topaz, and I have to fully WIPE my drive and reinstall everything again, which will take 2 full days to do. Needless to say, that’s 2 days of lost work and rest as a consequence.
Your previous post was not removed.
What has updating FFMPEG got to do with TVAI ?
Unless you have copied vanilla FFMPEG to the modified FFMPEG directory that TVAI uses.
Maybe post something like a dxdiag report or TVAI logs.
Same on PC, only it takes down the ENTIRE machine with it, not just the program.
I have removed everything I could find manually. I attempted to re-install the latest versions, they all crash. I attempted to roll back to the one from October, when I bought it, and it did work…now the installer says it cannot install because it’s not “valid” and keeps looking for the 6.0 installer. No reason why the PREVIOUS installer should be seeking out the NEW installer. I’ve wiped it all, cleaned out the Temp and Roaming and App folders…all to no avail. This is some janky software.
=================================================
No restore points in Windows?
yes I did this when it’s needed, overlay orig video with upscaled one in video editing software, a scene change helps to allignt both vids frame exactly and then I take over audio track from original.
Did you also wiped all this folders before new installation? You can copy/paste:
C:\Program Files\Topaz Labs LCC
C:\ProgramData\Topaz Labs LCC
%USERPROFILE%\Appdata\Local\Topaz Labs LCC
%USERPROFILE%\Appdata\Roaming\Topaz Labs LCC
I couldn’t believe my eyes, updated from 6.02 to 6.03 and then I get Variable Frame Rate with Model RheaXL, output h264 
but It was already late yesterday and I have to check again if this is really the case.
Guys, sorry to say this but for my peace of mind from now on I will assume Topaz is literally just trolling us at this point.
- With every so called ‘fix’ they (re)introduce others.
- Changes are so badly thought through, half implemented… inconsistent… etc
- This must be - idk - the 112th time the entire interface is changed again
- If one isn’t capable of developing a decent interface that can last and ehm… works, at some point in the process of trying, such valuable insight should manifest, yet it never does
So, at this point Topaz should stop trying to fix their Video AI interface themselves. They can’t do it. Period. They. Just. Can’t.
Get someone else, something else to do it for you, it’s cool ,no hard feelings. But DO it.
Ignoring this massive fail, taking years now, equals trolling.
Meanwhile, I’m seeing wild models on Github that can create crystal clear video from basically BLOB, for free, and here we have Topaz still doing their existential crisis thing.
I can’t be bothered listing all the things that are wrong and worse with this update… I just have no energy left for this.
7 Likes
Drop links to those GitHub projects here?
3 Likes
I definitely recommend contacting our support team (help@topazlabs.com).
A full Windows reinstallation won’t be necessary to fully uninstall previous versions of Video AI.
Yes please! We’d love to get a comparison thread going between our current models, other models, and our upcoming model which is going into beta this week.
3 Likes
First, it’s nice to hear that there’s a new model, so finally added functionality and not just messing with GUI and such.
But, I’d prefer refinement of the existing models (especially Iris V1 and 2 LQ and Rhea) instead of new, but also likely somewhat unpolished models.
E.g. We last had an update to an existing model with Nyx V3 I think but it’d be extremely nice if the generally good working (but with known flaws) models Iris and the promising but also quite unpolished Rhea got improved/refined.
Artemis is even at V12…
We’ve thought about this quite a bit, and this is my current perspective on model versions and naming:
There is only a finite amount of potential for model iteration, and I think a lot of our users think that we are making a choice between exploring a new model that attempts to perform beyond the limitations and weak points of a previous model, or trying to smooth out specific artifacting issues or limitations of an existing model.
For example, if Rhea was released as Iris v3, it probably would have been received differently but would still be the same model. Same could be said for Nyx, which easily could have been released as Artemis HQ v13. However, we think the progress and technical differences between Artemis and Nyx
In other words, the naming and labeling of models is something we’d like to simplify, and with the upcoming model we think we have made progress in simplifying the choice of selecting a model and knowing what it could be specifically good at processing.
6 Likes
Good time of day. I ran into this problem: after processing the video, it goes in jerks. This happens mostly with long-running videos (concerts, movies, etc.). What could be the cause and how to solve the problem? Has anyone else encountered this?
This is exactly what I thought when I first saw Rhea - it’s kind of an updated Iris with a bit of Nyx in it - so yes, I can see your point.
2 Likes
Fortunately it wasn’t and give us the ability to pass Rhea (standard) + Iris to get something “good”
