When I begun with Topaz Video Enhance AI we only Had Gaia HQ and Gaia CG. Processing a full movie took around 18 hours. Now with the latest version I can do the same work in between 4 and 8 hours depending on the mode I choose.
Yes, at that time, we are talking about how many seconds we need to process each frame (sec/frame) not fps.
And thinking about how days we need to process a single video.
My 1080p 2x Artemis speed is 6 fps. How did you manage to get 24 fps using 3090?
This topic starter uses the ProRes codec and the Artemis filter
double load on the processor - and he did not change the processor
I had a look into all reported benchmarks of the latest versions an none of them reached more than close to 16 fps in 2 x upscaling!
Yea, speed, but what about the quality?
Is it better than TVAI in quality?
Here is the benchmark from 3090:
https://community.topazlabs.com/t/video-ai-v3-3-x-user-benchmarking-results/46760/22
Artemis: 1X: 23.59 fps 2X: 12.31 fps
Thank you for correction, I have a typo in my last post, 24fps is for 1x Artemis, 12fps for 2x Artemis.
The real life result might be slower than the benchmark but it is big improvement compare to older version VEAI already.
Ok makes sense, thank you.
I guess CPU speed contribute to benchmark calculated fps. Since your newer CPU + 3000 GPU has better benchmark score than my older CPU + 4000 GPU. Either that or Topaz cannot make use of the full capability of 4090.
Iâm trying to figure out how significant is the CPU bottleneck or the slow fps I have is due to poor optimization for 4090. I canât just drop 100s of dollars to replace my CPU, ram, motherboard to test. Aside from spending the money to get a new CPU (which may or may not give me meaningful fps gain), I have tried variety of ways to off load work from CPU. I have tried using GPU encoder, which reduced CPU used to roughly 50-60%, yet no noticeable improvement in speed (maybe by 0.1 or 0.2 of fps). I have tried setting affinity of ffmepg to smaller number of cores. Again, no noticeable reduction in fps until I limit ffmepg to very small number of cores (1-4 cores). These testing suggest to me that even if I switch to the newest and top of the line CPU, the gain may not be big (like going from 6 fps to 15 fps for 1080p x2, like the benchmarks are suggesting).
The difference in quality is barely noticeable in CGI/IRL content, sometimes CAIN produces artifacts in certain scenes while Apollo does not and vice versa, but both types of artifacts are exactly the same type, distorted and blurred movements, especially in scene changes.
With the Chronos model Iâm quite satisfied, with a 1080 source I reach 50fps, not bad at all. Comparing with RIFE (as it is similar to Chronos as it is optical flow) the speed I get in the last 4.6 model in its TRT version and TTA/Ensemble enabled (this increases the quality but at the cost of speed) is 160fps, and going up. And the quality is exactly the same as Chronos in its latest version, it produces exactly the same small artefacts in the same places as RIFE 4.6 Ensemble, so I guess the devs implemented this technology to TVAI.
Make the comparisons yourself, I made them using: https://comparevid.com/
These are the videos:
-
pexels-lukas-rodriguez-17380073 (1080p)_CAIN-2x.zip (36.1 MB)
Compare it with:
pexels-lukas-rodriguez-17380073 (1080p)_apo8.zip (59.3 MB) -
pexels-lukas-rodriguez-17380073 (1080p)_RIFE-2x.zip (30.7 MB)
Compare it with:
pexels-lukas-rodriguez-17380073 (1080p)_chr2.zip (59.0 MB)
Do the comparison yourself and draw your own conclusions. My conclusions are that both models are similar, between them (talking about CAIN and Apollo), because they produce the same types of artefacts, although Apollo gives an extra smoothness that CAIN does not have, maybe because I have not configured the settings correctly in enhancr and I have not enabled the de-duplication of frames as I did with TVAI as it was enabled by default. I forgot to mention that both CAIN and Apollo support static elements such as film credits without any problem, it doesnât distort them or make the letters shake. And well, RIFE and Chronos are exactly the same, at least on how the results look.
If possible you could do both tests yourself and see how CAIN and RIFE make much better use of the GPU than the TVAI models. Although in order to use CAIN and RIFE in their TRT versions you would have to pay at least 7⏠to get the paid version of the program.
the 4090 has a tiny hardware switch where you can switch between âgamingâ power and âsilentâ use. please check if you have it on âgamingâ for the best performance.
That would depend on the model. Mine does not have that switch. I can control the mode in software. Gaming/silent mode does not make a difference in term of speed.
Okay, please check your power saving options in Windows next, especially the advanced settings. If the maximum cpu usage is set below 99 % you lose half of the fps!
Checked my power setting. My cpu maximum processor state is set to 100%.
i see a lot of compression, so much that one canât really compare beside the different compression pattern.
I did it with Resolve, here i can just turn videos of and on as with photoshop and layers.
The thing is i donât have the original file.
But i will take a look at enhancr.
You can download it for free from GitHub, but the paid versions are limited, you will only be able to use some models and only in NCNN version, to use TRT and others you will have to pay unfortunately.
Itâs good that youâre encouraged to take a look at it, if you try it, youâll see that CAIN is like Apollo and well, the speed doesnât compare at all with TVAI. The devs should also take a look at it and take it as a reference.
Topaz Video AI v3.3.2
System Information
OS: Windows v11.22
CPU: 13th Gen Intel(R) Core(TM) i9-13900K 31.715 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 40.09 fps 2X: 16.30 fps 4X: 04.47 fps
Proteus 1X: 35.82 fps 2X: 15.54 fps 4X: 04.80 fps
Gaia 1X: 15.72 fps 2X: 10.77 fps 4X: 05.08 fps
4X Slowmo Apollo: 43.83 fps APFast: 74.70 fps Chronos: 33.61 fps CHFast: 35.11 fps
This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.