This is quite annoying. Noticed same last night.
no it is not. it is shown the input size where you made the mark!
ah, I see. never mind. 
Very nice update, I can safely say I’ve seen notable improvements using Proteus in terms of processing speed at 2X (from a 1080p source) (benchmark results concur as well).
When will the sensible Auto Bandwidth be restored? I don’t know whether it was using AI to approximate or was just a default compromise, but it offered the best compression with near magical quality. Usually within 10-20% both up or usually down, capacity wise.
As it stands, Medium offers such massive bandwidth compression, that I cannot believe it offers the same level of quality and High is a redundancy nightmare bloating the sizes to over twice as much for no discernable difference.
Artemis High Quality is the best AI model for both FHD and UHD Blu-Rays, both to 4K and 8K and I recommend it to anyone whom wants this program to enrich their movies and series collection like I have.
Until AUTO is returned, I see no reason to renew my license ever again, even if Artemis somehow gets a new update after 2 years of stagnation.
As far as I know, this is the last patch containing the Auto Bandwidth function and the quickest: Topaz Video AI v3.2.2. Any version beyond it adds at least a full hour to the wait times for no reason whatsoever. Tested on both an RTX 3080 Ti and an RTX 4090.
Thank you for making this program. It was perfect even after you added +1 hour to wait times, because you soon also added audio conversion to AC3, but removing that perfectly balanced Auto Bandwidth function completely ruined this software for me past 3.2.2.
3 Likes
It’s as I said before, what a magnificent turn-around from the GR 4.0!
I’m thrilled to see the trajectory this prog is going!
3 Likes
Why is the UI getting laggier and laggier the more previews have been created?
Especially when working with 4K files, I notice that many UI interactions like selection playback location, going to next frame, starting a new preview, …, only start after some lag (even wait cursor might show up). The lag time seems to be proportional with the number of generated previews. It get’s pretty obvious after maybe 10 previews. After clearing up the previews, the lag is gone until more previews are generated again.
System: AMD 7950X, 4090, 32GB RAM, Win10
5 Likes
While I find Artemis especially great for most kind of animated movies and I sometimes use Artemis also for non-animated movies, I find the new Proteus 4 superior to it for non-animated movies. Especially the fine-tuning of noise reduction and other parameters is often an advantage over Artemis. Problems I had before with Proteus 3, like the temporal instability causing crawling patterns are now much better. The auto parameter mode also seems to be improved and I use it now much more often compared to previous Proteus.
Is it possible to disable EXR + DPX Rebuilt?
1 Like
As I mainly work with Iris and Nyx, I was eagerly anticipating the new update. Therefore, I would like to ask you, what can the other models do better that these two models cannot ? Good job, thank you.
Thanks for the reply, much appreciated. I was hoping for some image/video clip comparisons but I will take your word for it.
Here we go again… SAME BUG that i found in latest BETA =
When i use ENHANCEMENT AI for upscaling, and i want to use AI model like PROTEUS or IRIS, if i select first “MANUAL” Parameters with corret value with “Estimate” button, and turn the parameters in “Relative to AUTO”, i LOST all the values that i estimate from “Manual ( + Estimate)” values (and if i select AUTO parameters, and turn back in Manual mode, i lose all the previous estimate setting!
Everything is best seen in this video (in the video, the BUG is from BETA version, but with this latest stable version, is the same):
Please bring the situation as present in the previous stable version! 
1 Like
This is the intended behavior of the Relative to Auto/Manual selection dialog box. We will be keeping this new change to avoid confusion when applying settings in different modes.
For example, -50 in Manual is stronger than -50 in Relative to Auto, so keeping the values would imply that the setting has the same effect.
8 Likes
Hi guys. Is there any way I could get a link for the Linux build please? I signed up specifically to help test Linux version of Topaz Video AI, but I can not find links to Linux builds anywhere. Thank you for the update.
I am on Ubuntu 20.04.
2 GPUs:
- GeForce GTX 1070
- GeForce RTX 3060
It’s not my word, I am just parroting what the dev said in one of their response when they 1st released Prob4 for testing.
Love quality and speed improvement of Iris LQ. Thanks a lot!
Yeah, also had a problem with my stored preset. Needed to reconfigure it.
2 Likes
Very nice update. 
Issue: The presets do not retain the set output resolution and pixel type
1 Like
Thank you for your reply…I understand the choice, but I don’t fully agree with it: it should be clear that the “manual” settings are fixed settings, while the “Relative to Auto” settings are settings that are let’s say automatic but adapt to the values one sets to it by increasing or decreasing the sliders!
Keeping the setting as the “old” stable build, allowed to have much faster “relative to auto” settings adapted to the video analysis thanks to the “Estimate” button of the “manual” mode =
At this point, it would be very useful to have the “Estimate” button also in the “Relative to Auto” mode to have the most correct setting depending on the video you are upscaling, without each time going to “recopy” the analysis values in manual mode!
3 Likes
