Damn, you’re right!
The artifacting is as good as gone! 
I always love a bit of cripsy sharpness, but the negative effects were too much. I simply aborted the process, and started again, with your settings.
EDIT: I owe you one!
Bought the License for v3 two months ago…rarely used due to poor performance of the software. Now they come with a pretty decent update(Their claim) and they want me to buy the license again to use the software. No thanks. I will rather use some GitHub repositories for free which is far far better than this crap.
Bye
3 Likes
Thought that would make a difference.
I think that adjusting with ANTI-ALIAS / DEBLUR (cmd: preblur) will produce better results than adjusting the sharpening with SHARPEN (cmd: blur).
preblur
Adjusts both the antialiasing and deblurring strength relative to the amount of aliasing and blurring in the input video.
blur
Additional sharpening of the video. Use this if the input video looks too soft.
The value set should be relative to the amount of softness in the input video - if the input video is already sharp, higher values will introduce more artifacts.
For the ANTI-ALIAS / DEBLUR, a PLUS will set the value to DEBLUR and make the image sharper. Conversely, a MINUS will result in ANTI-ALIAS, making the image blurred.
1 Like
As soon as all models are downloadable and the program is usable offline I will venture an update from 2.6.4.
Another useless answer.
Huh? How would buying a license only last 2 months? What happened here?
1 Like
Poor thing.
2 Likes
Your license should still be valid for v3.1 if was bought 2 months ago. If you can’t login you should contact support.
1 Like
The old perpetual licence model worked on major version releases. So you could buy V1 and 3 months later V2 is released and you don’t get any updates. Topaz is much better as you get 1 year of updates, which is a much fairer way of doing things.
huge upgrade to performance so thank you. just got one question. any word on av1 support for amd 7900 xtx or xt cards? also smart access video or ai accelerator support for amd?
I always wondered what the heck a negative antialiasing did. TIL.
2 Likes
The latest update crashes already when creating a preview.
Settings: Motion Deblur, Enhancement: Progressive, Artemis, Strong Halo.
The creation process stops almost at the end of 15 secs and the preview video is not finished.
Although I am eternally grateful for your tweaks, and the woman with the red lips looks a whole lot better (when does a woman with red lips ever not look good? 
), I ran some extra experiments. A nose closeup with your current settings:
Still too much artifacting, IMHO. So, now with sharpen = 0
Better, of course; but, for upscales, I really like that bit of antialiasing, so I flipped the sign on AA again:
Looking very good. Then add some minute dehalo-ing:
Got a clearer picture, but crispier nonetheless, and staying on the ‘good’ side of AA (aka, getting rid of the zig-zaggies).
1 Like
Good speedup in this version. 7950x & 4090.
An issue:
1080p25 to 4k50p. proteus auto. fast chronos
I am getting a 1 frame blend instead of cut between some scenes
Scene detection should stop this from happening.
I’ll try non-fast chronos next time but it should be safe from 1 frame blends in either mode.
edit: same issue on chronos. A cut between two shots is becoming a 1 frame blend. The AI model does not seem to effect it
input file is prores 422 1920 1080 25p
1 Like
Jup. Same issue here. System is Mac OS Ventura on a 16GB Mac Mini M1. That preview thingy is slowly getting nerving. Sometimes preview shows in split screen left and right completely different videos, parallel upscaling of >1 Videos is in progress.
Sometimes I really miss the quad preview from V2.6, and also it’s flawless preview during encoding. Please further optimize that in 3.x somehow…
Otherwise the the last few releases was worlds away from the initial - super buggy - 3.0x releases- The 3.x branch is heading towards the right direction ;o)
1 Like
What your seeing from scene to scene is why just using the estimate in proteus never seems to work over an entire video. The real trick and this takes some trial and patience is using ‘Relative to Auto’. Hopefully the video is fairly consistent with the type of problems from scene to scene. What won’t be consistent is the values to repair the problems. Relative to Auto goes a long why to help with the problem.
I also try to limit my upscale to 2x or a max of 225 percent for a single pass with TVAI. I also if I’m working with a very low res input file I will use conventional methods to do a slight upscale for generally a better result. Say 512 width to 640 or 720 to 854. It’s not much but I find that it helps. I also do these at a lossless or very close to lossless conversion.
2 Likes
I posted this in another topic but it didn’t get any traction. Could someone test downscaling a video? Version 3.1.0 is taking magnitudes longer than version 3.0.12 to the point that it’s unusable. Upscaling is also much slower. Thanks.
That is the sort of thing that makes me abort the entire process. Hope they fix it for you soon.
Yeah, I always tweak ‘relative to auto’. I just had no idea sharpening had such detrimental effect on the overall picture quality (for some reason, I got it in my head it would just work on edges).
Yeah, same here. In fact, with video that is too low-res, I scale up a bit (Lanczos), then let TVAI take over. The trick, I found, is to allow for enough scale ‘room’, as it were, for TVAI to perform a usable, visibly repaired upscale, but not let it come from such low res that it starts mangling faces.
