Topaz Video AI v3.1.4

Is it true. Chronos ruined all my clips. Two months wasted in vain. Now I’m trying Apollo. Made 3 clips. Looks like no artifacts

1 Like

Well now I’ve found a batch of videos that were recorded at 30 fps from a PAL 25fps source - and they contain many duplicates throughout, of exactly the kind that should be removeable by TVAI.

Unfortunately, I am still evaluating version 3.1 and it cannot be tested due to the large and flickering Topaz watermark - it seems to be added before the duplicate removals and if so, obviously prevents many of the duplicates being seen by the software as duplicates so many of them remain. Second runs aren’t possible of course. Either that, or duplicate removal doesn’t work properly.

This could have been the feature that persuaded me to renew/upgrade but I’m not willing to guess, so I won’t. Topaz seriously should stop that watermark from flickering, or add it after all other processing, otherwise the trial cannot be used for the purpose it is intended: evaluation of the software.

Looking at the fact that sometimes there are problems, I ask the developers to pay special attention to the good work of upscaling and converting to 4k, 120 fps! I overtake any video, DVD, HD in 4k, 120 fps.
It takes a very long time, a clip of 4 minutes is processed for 3 hours. But the result is above all expectations. Fabulous. Fantastic…

1 Like

LOL Thanks very much Marty. : )

1 Like

I have a weird pretty eratic error:
Sometimes Videos get processed without any issue. The same Videos with the same settings produce a black screen when rendering preview while windows is still working (you can still hear youtube videos playing without any issues). Sometimes preview works fine, but export get´s me a blank screen.
According to the log file the video card wasn´t available anymore. I´ve set the max memory usage to 80% und acitvated the “low power” option. I use the latest NVIDIA Studio driver.
I have an RTX 3090 and VRAM usage never get´s over 4 GB. This error occurs since VEAI 3.1 and the introduction of Tensor Core usage.
I also train GANs on that card with nearly 100% VRAM usage (24 GB) and no such error ever occured. The GPU is not overclocked.
Anybody else here with such crashes?

edit: by blank or black screen i don´t mean VEAI going black/blank, the whole Win10 GUI goes black and the monitor goes into sleep mode. You even can´t reactivate the GUI by pressing shift/ctrl/win/B.

I was getting patches like those with Chronos fast. They stopped when I started using the slomo mode. So if I want to make a 30 fps movie 60, I set Apollo to slomo 2x and the output to images. (You can do it with Chronos too.) Once it’s done, I use another tool to convert the images back into a video and add the sound, chapters, and subtitles back in.
Doing it this way has fixed all the blur patches I saw before when using Chronos fast. (It’s been awhile since I’ve ran a frame interpolation video, but I see no reason why this should have changed.)

Humm, it gives that message even when it works. This is while running Apollo and it’s working fine:


Sadly, if there is no message for the actual error, it still finds those error messages and makes it seem like they are the issue.

FEATURE REQUEST: A way to mark previews in the GUI.

I would love to be able to mark previews when I am going through a bunch of them to find the optimum settings for a project. Maybe a simple check mark or flag (keep and reject)? Or maybe a 5-star system? This feature would simplify my workflow.

4 Likes

Me too. Proteus with 4x upscaling gives black splotches.

1 Like

Some previews and videos are still getting stuck at 99% or taking forever to complete right at the end.

Also, duplicate frames removal doesn’t always seem to work if there are multiple duplicate frames in a row. I’m still getting a pause in certain videos that have this issue, even after some duplicate frames were removed. It’s smoother than before, but not perfect.

Do I need to change the framerate at all when removing frames?

1 Like

Please post your situation.

1 Like

It’s duplicate frames replacement so if implemented correctly, with no speed or frame rate change, the total number of frames should remain the same.

Obviously, if you intend to create slomo or higher frame rates, it will change to whatever you set it to.

But there are many reasons for jerky videos and dup frame replacement will only fix some of them.

ffmpeg "-hide_banner" "-nostdin" "-y" "-nostats" "-i" "i.mp4" "-sws_flags" "spline+accurate_rnd+full_chroma_int" "-color_trc" "2" "-colorspace" "2" "-color_primaries" "2" "-filter_complex" "tvai_up=model=prob-3:scale=0:w=5120:h=2880:preblur=0:noise=0:details=0:halo=0:blur=0:compression=0:estimate=20:device=0:vram=1:instances=1,scale=w=5120:h=2880:flags=lanczos:threads=0" "-c:v" "prores_videotoolbox" "-profile:v" "lt" "-pix_fmt" "p210le" "-allow_sw" "1" "-map_metadata" "0" "-movflags" "frag_keyframe+empty_moov+delay_moov+use_metadata_tags+write_colr " "-map_metadata:s:v" "0:s:v" "-map_metadata:s:a" "0:s:a" "-c:a" "copy" "-metadata" "videoai=Enhanced using prob-3 auto with recover details at 0, dehalo at 0, reduce noise at 0, sharpen at 0, revert compression at 0, and anti-alias/deblur at 0. Changed resolution to 5120x2880" "i_prob3_temp.mov"

There are no black splotch/blob artifacts with 2x upscale.

Please Add option or future like (Shut Down When Finished)
it will be cool to big files and Saving time and energy, and therefore electricity bills.

2 Likes

It is something that has been asking for years… something so essential and there is no way :frowning_face:

1 Like

Yes, I tried it. It doesn’t work now. If a file has been modified and you start TVAI, it launches the installation prompt to download that file again. Kinda like there’s a watchdog at the start of the application now that detects modified files.

Testing on a short image sequence, I can see the speed improvements, so I tried to do a full sequence except am running into problems.

Now when importing the whole image sequence, the speed drops to 1/4 what is was doing with the original sequence, will run for about 20 seconds, does 31 frames then “completes” with a green checkmark.

I tried with a smaller sequence again and speed is normal and it doesn’t stop processing prematurely.

Is there a limit to the image sequence size that can be imported before it can’t process?

on M2pro getting “unknown processing error” message in 3.1.4

1 Like

It names them with 6 digits, so probably once you go over that. But I’m pretty sure you can bypass that in the CLI if it really does limit there.

u can use auto shutdown app temporarily until available this option in future.