Video Enhance AI v2.0.0

g.lukosevicius · March 14, 2021, 8:31pm

The same issue with PAL. Field order does not matter. And in most cases it is red color, or in more rare cases some other more saturated colors. Need for manual deinterlacing with other tools was stoping me from purchasing the earlier versions of Video Enhance AI. Interlaceing support is available now, but not something to be usefull Lets wait for the next release.

Btw, when I try to add image to the post it says “Sorry, you can’t put images in a post”. How you guys are adding them?

carpentergeek · March 14, 2021, 11:04pm

I do the same thing but with cuda hardware excel:
md 8bit_265
for %%x in (.m) do (ffmpeg.exe -hwaccel_output_format cuda -i “%%x” -pix_fmt yuv420p -c:v hevc_nvenc -preset slow -rc vbr_hq -b:v 10M -maxrate:v 15M -c:a copy 8bit_265/“%%~nx”.mp4)

edit: apparently the star or wild card character doesn’t show up here which is needed: for %%x in ([star].m[star])

deepzone · March 14, 2021, 11:49pm

Hope this is fixed in the next version. It’s reported to the bug list i assume ?

czerkin · March 15, 2021, 1:54am

I think it’s a file size or image format.
I’m dragging and dropping to input field using png and it’s ok.

I’ve tried the v2.1.0 beta version, this issue hasn’t been fixed yet.

paul-4464 · March 15, 2021, 9:21am

I think that’s a good idea until it’s fixed.

Palmplex · March 15, 2021, 1:59pm

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.

shodan5000 · March 15, 2021, 4:49pm

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

robert.niessner · March 15, 2021, 6:54pm

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.

deeImgGuy · March 15, 2021, 8:15pm

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.

shodan5000 · March 15, 2021, 9:14pm

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

robert.niessner · March 16, 2021, 12:22am

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.

Palmplex · March 16, 2021, 4:16am

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

Palmplex · March 16, 2021, 9:38am

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

robert.niessner · March 16, 2021, 11:39am

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

aaron.lee · March 16, 2021, 11:51am

@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!

deepzone · March 16, 2021, 1:44pm

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

Chase · March 16, 2021, 1:59pm

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.

lee.keels · March 16, 2021, 4:59pm

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

taylor.bishop · March 16, 2021, 5:31pm

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.

Dylan_V · March 16, 2021, 5:40pm

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.