Video Enhance AI v2.1.1

Exactly. A simple button on “preferences” would be enough for anybody.

Actually no.
e.g. if you have a 25 fps video an you get 5 fps, it is easier to multiply the minutes of the video by 5 (25/5 = 5 times x realtime) to get a fast estimation in your head.

That would be true if VEAI would show you the duration of the video - but it only shows frame numbers.
I pretty much prefer the Sec/Frame as this is the same with most professional software I am using like for example After Effects or Blender. For long renders I find it much more informative to see how long it will take to render per frame.

But as this is a matter of personal preference I also would like to see a toggle for what to display. :slight_smile:


I always liked the “x realtime” feature of After Effects, hated the sec (or minutes or even or days during the 90’s on Amiga)/frame on LightWave.
But, as you and shodan5000 said, it is a personal preference thing.
So, we ask for a button! LOL

Oh the good old days:
Lightwave 3.5 on Amiga 1200 - a 12 sec animation in SD took me a week to render

1 Like

Gaia used to be really good as you said. But the Artemis models are significantly a lot better than they were before.

A user here made a really good post on what models to use for certain types of media. You can check it out here.
Video Enhance AI v2.0.0 - Product Releases / Video Enhance AI - Topaz Discussion Forum (

1 Like

You can find it here with more in depth information.
VEAI Models + Performance Guide


Heavily appreciated. Thank you.

You forgot one small detail. It is useful to have a copy of the cumulative updates. Because let’s imagine for some A reason x or y there is a big bug in Windows. You must use a backup of before this bug. But in the meantime there have already been cumulative updates that are not in the backup. To avoid downloading them again, it is good to reinstall them from the previously downloaded copy.

I mean in all honesty, you’d have to be on a dialup connection for an update download to really matter. I would not waste a single second of my time to “avoid downloading them again.” Just not worth it.


This text will be hidden

Any new versions of Gaia yet ? I’m using Gaia v6 to work on some raw footage from The Man From Earth the director sent over. Artemis removes too much detail… Gaia is waaay better to keep the details.
Tried all of the Artemis models and all of them butcher the fine details.


That film was shot in SD if I remember correctly? Lots of very dark scenes in the house, very noisy footage.
EDIT: yeah, shot on the DVX100.

Artemis MQ works fine for me, but you should raise the exposure of the footage before feeding it to Artemis. Then it won’t remove the details, just the noise.
That’s what I did with raw footage from our film and it works great that way.

Would you mind telling the director of “The Man from Earth” that I really enjoyed his film and would like to say thank you for some intelligent entertainment he created.

1 Like

Hello, I still have this problem which appears during encoding, I switch to low, medium or high, it does the same thing. Can you help me ? It didn’t do that to me a week ago. help me @taylor.bishopCapture

1 Like

No problem, will deliver the message to him :slight_smile:
DVX100… that may explain why it’s a 3:2 pulldown on the dv footage.
He probably filmed in 24p mode.

I am not sure about the 24p mode. This is what I found on a site about the 2017 remaster for Bluray:

The original DV 30 Mbps 29.97fps media was converted to a new ProRes 422 HQ 220 Mbps source at 24 fps for more cinematic motion and for more control and manipulation of the picture during an all new color correction process, with each shot meticulously noise reduced, sharpened, and detail enhanced.

If he really had filmed in 24p then why would he had done a conversion?

EDIT: Found this about the DVX100A - it has two modes:

24p Standard utilizes the same 2:3 or 3:2 pulldown cadence long used to transfer 24fps film to NTSC video. The first 24p frame is written to two fields of 60i video, the next is written to three, the next to two, and the next to three again

24p Advanced uses a syncopated 2:3:3:2 pulldown cadence to stuff 24 frames into 60 fields. It’s ever so slightly different in its playback; the standard cadence of 2:3:2:3:2:3:2:3… evenly intersperses the “short” and “long” frames, while 2:3:3:2:2:3:3:2… lumps two “short” frames together followed by two “long” frames. The difference is subtle, but can be seen on smooth pans or on regular in-frame motion, like the passage of a train. In my experience so far, about half the people looking at a 24p Advanced clip can see that the motion is a bit different, and half cannot.

But 24p Advanced isn’t intended for making the 60i video look like film; it’s designed to allow the best possible recovery of the original 24 frames. You’ll note that all four original frames can be recovered from self-contained 60i frames; the green frame in 60i now contains the “extra” B and C fields and can be discarded, since all the information for B is contained in the yellow frame, and all the information for C is in the magenta frame.

Extracting a true 24p clip from a 60i recording simply requires copying the raw data for the red, yellow, magenta, and blue frames into a new 24p file, skipping the green frame altogether. No decompression or recompression is required, and all recovered 24p frames retain first-generation quality. No clipping or other loss is incurred; you are still working with all your frames in their first-generation glory in 24p.

please please please fix the jpeg output… especially during fade ins and outs there is horrific jpeg quality.

please compare:

Ok. So i was right saying to him that the footage i got was not “pure” dv footage.

Here is a comparison of the different models :

Lower VRAM usage in the Preferences. Reduce machine load.

Roll back to the 461.92 game drivers/the latest studio drivers.

Is it just me who thinks previous AI models had better results?

The new AI models, v10, v11 and v12 seem to be overdoing what v9 was doing almost perfectly.

Does anyone else think the same?

1 Like