Video Enhance AI v2.0.0

Thx and yes for a long piece of content that’s a good idea , but why have all that technology to improve the image when the audio is completely useless. I have hours and hours of DV content I what to share many clips for personal use. It’s useless if I have to re-edit and load & scrape the audio from a 7GB DV file for a 20 second clip ! That’s not fit for purpose. The only reason I bought this software was for this very purpose of deinterlacing and creating smooth 50fps video from my 25 year old content.

1 Like

It’s just seems confusing how the audio is STILL in the shoddy state that it is in.

1 Like

You can re-insert your audio very fast without re-encoding it via VirtualDub2 (=VD2).
Let’s say you have a 1 hour DV clip.

  • Load your DV clip into VEAI and let it do the deinterlacing & upscale into ProRes MOV.
  • Load that MOV into VD2, set in the menu “Video >> Direct stream copy”, then in the menu go to “Audio >> Audio from other file” and select your DV avi as source.
  • Go to “File >> Save Video” and in the new window change your file type to MOV, select destination folder and file name and click “Save”
    Now it will stream copy audio and video into a new file without re-encoding. Should take only a short amount of time.
1 Like

I think the problem he is talking about is when he uses VEAI on a 20 second clip in the middle of a long DV - still not all that hard to pull the audio from that section, but not as easy as adding audio for the whole thing.

True, but this shouldn’t have to be done. Sorry, I expect better than this for this product.

OK, but then he could use the nowadays free tool Scenalyzer Live 4 to import his DV clips and use Scenalyzer’s auto scene detection to split the clips before doing any other work.

Thanks Robert, Scenalyzer is brilliant. Thankyou. It even detects the 16:9 and 4:3 flags which I notice that VEAI does NOT seem to use. Is there anyway to make VEAI recognise aspect ratio flags? I can’t even find a way to manually change the aspect ratio in VEAI. You can change the image size selection in “Size” but not the aspect ratio. Thanks in advance

Robert: Years ago I’d already captured all my MiniDV tapes to DV files within an avi. 1 tape = 1 file , they are not split. Scenalyzer will identify all the scenes within 1 file but is there any way to output the individual clips to separate avi files so i can select which ones for VEAI? I can’t see any “output to file” or save to file for clips. (I’m not going to recapture all my tapes again as my DV player has died). Thx

Yes, there is. (I am translating the GUI from the German version of Scenalyzer, so it might be labelled differently in the English version)

  • press CTRL+SHIFT+A to add your AVI files (or menu “Clips >> Add AVI files”)
  • select the clips you want to have analyzed; right click for the pop-up menu and select “Clips >> Scene detection…”
  • in the new option window select the type of scene detection - if your camera had timecode select scene detection by date, otherwise select “optical / visual” and the sensitivity level
  • click OK and it will start to analyze the clips, when finished you will see several film strips with the detected scenes (nothing has been written until now)
  • select all scenes and click the red “OK” in the lower middle tool bar - or press CTRL-O
  • a warning pops up - don’t panic - it won’t delete your original clips, despite the warning
  • click “OK” and it will start to stream copy your scenes into individual clips into your selected output folder (= capture folder)

Works like a charm :slight_smile:

1 Like

@taylor.bishop v2.1.0.0b top notch. so far I feel like this beta has hit many many improvements that just work. The SPACE bar pausing the preview for example, just works. Keep it up, thank you!

1 Like

any idea if they have improved the deinterlacing and if they have synced the audio yet ?
Any new models ? :slight_smile:

Dione TV and TD are updated to version 3. Artemis LQ and MQ are updated to version 12. Dehaloing is removed from Artemis LQ & MQ, and Dione TD, and moved to their own separate models. It’s still somewhat hazy, but it appears they have implemented some kind of masking, so that the “haze” is now limited to the areas of the frame that are being dehaloed.

1 Like

You don’t want the audio even if they do sync it. The output audio is very low quality.

1 Like

We’ve got video I/O and audio syncing issues lined up for the May release. So a bit longer, but it’s the next major thing on our roadmap to tackle.

4 Likes

I was wondering if they’ve said anywhere if they’re going to add a detelecine filter to the deinterlacing models? Probably a ways down the road, but it would be great to be able to get a film-based source back to its original 24fps.

Do the Gaia models plan on getting updated soon? I’ve used them a lot in the past, but now the results they produce just look really bad.
I use VE AI to enhance CG-related media (some irl stuff included) and every AI model except for Gaia are able to produce much better results.

Can I make a stupid question?
What happens using Dione on a progressive source? Does it mess up results?

The Gaia models are indeed in a dire need for an update, but depending on the source Gaia HQ still yield amazing results when feeding it good quality RL/3D-type inputs.

Gaia CG in the other hand is fairly similar to madvr’s NGU AA, in a sense where it upscales cartoon/anime-type inputs while staying true the source. (No nonsense “enhancements” are applied which only ruin the overall quality more than anything.)

1 Like

Ahhhh , that works. Thanks Robert. It’s not intuitive at all !! Perfect

After like a month upscaling hundreds of blu-ray ripped movies + old torrent ones. This is how I sum up all of the models that will give you the best result for the source input.

*Artemis HQ v11 => for good quality movies, films with at least 4000kbps+ bitrate for 720p, 6000kbps+ bitrate for 1080p. I use this most of the time for present blu-ray sources from 2010 till now.

*Artemis MQ + LQ => halo effects with trees and bushes for videos under 720p only. Best for 720p + 1080p with medium compression + artifacts only.

*Artemis AA + Gaia CG => same thing with minor differences. Pick Artemis AA for fast + medium quality. Pick Gaia CG for slow + good quality. I only use these models when my source input is 480p or 720p (bad quality). This will slightly sharpen and reduce noise + block without having weird faces or blurry effect from Artemis MQ + LQ. I recommend using Artemis AA if movie, Gaia CG if anime.

*Gaia HQ => Artemis HQ on steroids, but motion consistency is what I don’t like. Recommended for 720p and above with medium compression and artifacts. Best with 1080p with <1% motion flicker. Good for slow movies, bad for fast paced movies. Only use if Artemis MQ + LQ can’t please you. Otherwise, use Artemis HQ if the input is already considered good.

*Theia Fidelity + Detail => Artemis with customization, only use if you know what you’re doing. That’s it. If you don’t, ignore it.

*Dione => sorry, still not have enough time with it since most of my sources are Progressive.

–TL;DR:

*720p/1080p above medium/good quality => Artemis HQ for fast, Gaia HQ for slow but more details (consider using it if your source has medium quality)

*480p/720p under medium quality => Gaia HQ

480p/720p @&$ quality => Gaia CG (slow speed-good quality-motion flickering)/Artemis AA (fast speed-medium quality-less motion flickering)

9 Likes