Video AI v3.2.X - User Benchmarking Results

ForSerious · May 3, 2023, 2:03pm

I put my 3080 in this machine for a night:

Topaz Video AI  v3.2.3
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7900X 12-Core Processor              31.746 GB
GPU: NVIDIA GeForce RTX 3080 Ti  11.816 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 22.87 fps 	2X: 15.32 fps 	4X: 4.31 fps 	
Proteus		1X: 21.77 fps 	2X: 15.85 fps 	4X: 4.22 fps 	
Gaia		1X: 8.00 fps 	2X: 5.51 fps 	4X: 3.67 fps 	
4X Slowmo		Apollo: 30.61 fps 	APFast: 58.20 fps 	Chronos: 17.66 fps 	CHFast: 28.54 fps

I posted this one before but got all the models to work this time:

Topaz Video AI  v3.2.4
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7900X 12-Core Processor              31.746 GB
GPU: AMD Radeon RX 6900 XT  15.954 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 12.68 fps 	2X: 8.45 fps 	4X: 3.01 fps 	
Proteus		1X: 12.20 fps 	2X: 8.06 fps 	4X: 3.02 fps 	
Gaia		1X: 6.12 fps 	2X: 4.23 fps 	4X: 3.01 fps 	
4X Slowmo		Apollo: 12.24 fps 	APFast: 32.51 fps 	Chronos: 8.70 fps 	CHFast: 14.32 fps

Also, with PNG output, these numbers are actually the same as running a real movie on this machine.

Chamberhouse · May 3, 2023, 5:02pm

Hi - is that a 48 or 64 core GPU, please?

Thanks.

Andy

memo90061 · May 3, 2023, 5:09pm

It is the 48 GPU. I bought an M2 Max MacBook to try it out and returned it. The numbers were very similar to the Mac Studio Ultra. The MacBook M2 Max seems like the better deal if the numbers are the same.

Wombart · May 3, 2023, 7:58pm

Topaz Video AI  v3.2.4
System Information
OS: Windows v11.2009
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: 34.37 fps 	2X: 19.46 fps 	4X: 5.76 fps 	
Proteus		1X: 29.81 fps 	2X: 17.89 fps 	4X: 5.86 fps 	
Gaia		1X: 13.94 fps 	2X: 9.50 fps 	4X: 5.75 fps 	
4X Slowmo		Apollo: 38.91 fps 	APFast: 73.69 fps 	Chronos: 27.63 fps 	CHFast: 32.32 fps

Topaz Video AI  v3.2.4
System Information
OS: Windows v11.2009
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: 3840x2160
Benchmark Results
Artemis		1X: 7.31 fps 	2X: 4.32 fps 	4X: 1.27 fps 	
Proteus		1X: 6.28 fps 	2X: 3.93 fps 	4X: 1.26 fps 	
Gaia		1X: 3.03 fps 	2X: 2.09 fps 	4X: 1.27 fps 	
4X Slowmo		Apollo: ERR fps 	APFast: 22.76 fps 	Chronos: 6.24 fps 	CHFast: 11.36 fps

memo90061 · May 4, 2023, 3:06am

Does anyone have an i7-13700k with a 4080 or 4090? Curious about the numbers.

david.123 · May 4, 2023, 6:55am

Topaz Video AI  v3.2.4
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7950X 16-Core Processor              63.14 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
GPU: AMD Radeon(TM) Graphics  0.47446 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 41.72 fps 	2X: 19.34 fps 	4X: 4.93 fps 	
Proteus		1X: 37.12 fps 	2X: 17.83 fps 	4X: 4.85 fps 	
Gaia		1X: 14.92 fps 	2X: 10.62 fps 	4X: 5.01 fps 	
4X Slowmo		Apollo: 42.07 fps 	APFast: 65.26 fps 	Chronos: 32.15 fps 	CHFast: 36.16 fps

rfrankway · May 4, 2023, 2:37pm

Topaz Video AI  v3.2.3
System Information
OS: Mac v13.0301
CPU: Apple M2 Max  96 GB
GPU: Apple M2 Max  72 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 10.94 fps 	2X: 7.52 fps 	4X: 2.64 fps 	
Proteus		1X: 10.81 fps 	2X: 7.11 fps 	4X: 2.50 fps 	
Gaia		1X: 3.38 fps 	2X: 2.52 fps 	4X: 1.99 fps 	
4X Slowmo		Apollo: 9.15 fps 	APFast: 31.15 fps 	Chronos: 3.65 fps 	CHFast: 6.01 fps

Topaz Video AI  v3.2.4
System Information
OS: Mac v13.0301
CPU: Apple M2 Max  96 GB
GPU: Apple M2 Max  72 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 10.93 fps 	2X: 7.46 fps 	4X: 2.96 fps 	
Proteus		1X: 10.98 fps 	2X: 7.40 fps 	4X: 2.54 fps 	
Gaia		1X: 3.35 fps 	2X: 2.52 fps 	4X: 1.97 fps 	
4X Slowmo		Apollo: 9.25 fps 	APFast: 27.91 fps 	Chronos: 3.69 fps 	CHFast: 6.05 fps

kevin.purdy · May 4, 2023, 3:55pm

Using the Intel Arc Beta v4335 drivers

Topaz Video AI  v3.2.4
System Information
OS: Windows v10.2009
CPU: 11th Gen Intel(R) Core(TM) i7-11700K @ 3.60GHz  31.771 GB
GPU: Intel(R) Arc(TM) A770 Graphics  15.875 GB
GPU: Intel(R) UHD Graphics 750  0.125 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 10.35 fps 	2X: 4.74 fps 	4X: 1.48 fps 	
Proteus		1X: 7.79 fps 	2X: 3.78 fps 	4X: 1.20 fps 	
Gaia		1X: 5.49 fps 	2X: 3.64 fps 	4X: 2.88 fps 	
4X Slowmo		Apollo: 7.15 fps 	APFast: 20.69 fps 	Chronos: 5.49 fps 	CHFast: 9.30 fps

AttorneyWoo · May 4, 2023, 4:51pm

Topaz Video AI v3.2.4
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 7 3700X 8-Core Processor 15.927 GB
GPU: NVIDIA GeForce RTX 4070 11.744 GB
Processing Settings: device: 0 vram: 0.95 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 16.70 fps 2X: 8.62 fps 4X: 2.29 fps
Proteus 1X: 14.54 fps 2X: 8.55 fps 4X: 2.26 fps
Gaia 1X: 6.02 fps 2X: 4.13 fps 4X: 2.40 fps
4X Slowmo Apollo: 21.93 fps APFast: 35.01 fps Chronos: 12.78 fps CHFast: 17.14 fps

roldog · May 4, 2023, 5:40pm

Topaz Video AI  v3.2.4
System Information
OS: Windows v11.2009
CPU: 11th Gen Intel(R) Core(TM) i9-11900KF @ 3.50GHz  63.831 GB
GPU: NVIDIA GeForce RTX 3080 Ti  11.816 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 21.36 fps 	2X: 14.05 fps 	4X: 3.62 fps 	
Proteus		1X: 18.62 fps 	2X: 9.44 fps 	4X: 3.83 fps 	
Gaia		1X: 7.89 fps 	2X: 5.42 fps 	4X: 3.49 fps 	
4X Slowmo		Apollo: ERR fps 	APFast: 53.65 fps 	Chronos: 17.65 fps 	CHFast: 24.39 fps

catchoro · May 5, 2023, 5:37pm

Nice performance uplift in the 3.2.4! I had to run twice the 1080p test to check if I got something wrong.

ForSerious · May 5, 2023, 6:26pm

That’s a little odd that you got so much improvement. I run my similar branded machine (AMD 5000 CPU/Nividia 3080 GPU) and only saw an increase in Apollo speed. All the others were the same.
Did you change the Max Memory Usage percent, or enable EXPO on your RAM?
(Your chart is nice, but seeing the benchmark printout helps us see a little bit more context.)

catchoro · May 5, 2023, 10:28pm

Oh, thanks for noticed. I made a wrong cut at the top of the image. Fixed, my bad.

The only change in the hardware I believe it happened in between versions was from 3.2.1 and 3.2.2 where I switched the system from HDD to SSD. It didn’t made much of a difference since my temp folder was already in the other SSD, only when I was testing 7k because it needs more than 32 ram and the system frozen trying to swap that ammount of data in the HDD, lol. With the SSD the system can swap, but I stopped the test because I can’t have the PC working for 15h to render 2min test (I believe with more RAM it could improve, but I’ll upgrade it in the future if/when other applications need it).

fess · May 7, 2023, 12:45pm

Cheap Xeon config:

Topaz Video AI  v3.2.4
System Information
OS: Windows v10.2009
CPU: Intel(R) Xeon(R) CPU E5-2678 v3 @ 2.50GHz  95.907 GB
GPU: NVIDIA GeForce RTX 3060  11.845 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 9.26 fps 	2X: 5.90 fps 	4X: 1.64 fps 	
Proteus		1X: 8.53 fps 	2X: 5.12 fps 	4X: 1.57 fps 	
Gaia		1X: 3.10 fps 	2X: 2.13 fps 	4X: 1.41 fps 	
4X Slowmo		Apollo: ... fps 	APFast:  -  fps 	Chronos:  -  fps 	CHFast:  -  fps

Topaz Video AI  v3.2.4
System Information
OS: Windows v10.2009
CPU: Intel(R) Xeon(R) CPU E5-2678 v3 @ 2.50GHz  95.907 GB
GPU: NVIDIA GeForce RTX 3060  11.845 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 3840x2160
Benchmark Results
Artemis		1X: 1.98 fps 	2X: 1.24 fps 	4X: 0.34 fps 	
Proteus		1X: 1.84 fps 	2X: 1.12 fps 	4X: ... fps 	
Gaia		1X:  -  fps 	2X:  -  fps 	4X:  -  fps 	
4X Slowmo		Apollo:  -  fps 	APFast:  -  fps 	Chronos:  -  fps 	CHFast:  -  fps

ForSerious · May 9, 2023, 1:19am

Topaz Video AI  v3.2.4
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7900X 12-Core Processor              31.746 GB
GPU: NVIDIA GeForce RTX 4070 Ti  11.729 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 24.61 fps 	2X: 15.17 fps 	4X: 4.45 fps 	
Proteus		1X: 22.56 fps 	2X: 15.39 fps 	4X: 4.33 fps 	
Gaia		1X: 8.25 fps 	2X: 5.73 fps 	4X: 3.81 fps 	
4X Slowmo		Apollo: 35.33 fps 	APFast: 63.65 fps 	Chronos: 18.44 fps 	CHFast: 29.34 fps

ant · May 9, 2023, 5:21pm

Topaz Video AI  v3.2.4
System Information
OS: Windows v11.2009
CPU: Intel(R) Core(TM) i7-10700K CPU @ 3.80GHz  31.924 GB
GPU: NVIDIA GeForce RTX 4080  15.688 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 25.68 fps 	2X: 11.34 fps 	4X: 3.93 fps 	
Proteus		1X: 20.74 fps 	2X: 10.26 fps 	4X: 3.85 fps 	
Gaia			1X: 10.18 fps 	2X: 6.96 fps 	4X: 4.03 fps 	
4X Slowmo		Apollo: 29.76 fps 	APFast: 50.94 fps 	Chronos: 22.14 fps 	CHFast: 24.82 fps

david.123 · May 10, 2023, 6:40am

Topaz Video AI  v3.2.5
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7950X 16-Core Processor              63.14 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
GPU: AMD Radeon(TM) Graphics  0.47446 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	42.33 fps 	2X: 	18.95 fps 	4X: 	04.97 fps 	
Proteus		1X: 	36.59 fps 	2X: 	18.76 fps 	4X: 	04.74 fps 	
Gaia		1X: 	15.74 fps 	2X: 	10.87 fps 	4X: 	04.93 fps 	
4X Slowmo		Apollo: 	41.00 fps 	APFast: 	64.74 fps 	Chronos: 	32.15 fps 	CHFast: 	36.57 fps

topaz257 · May 10, 2023, 10:27am

79050 + 4090 + DDR5-6200CL30
Compared to benchmark prior to this one with same CPU + GPU, there is a bigger difference in 4X performance which is most likely primarily due to RAM speed differences.

rfrankway · May 10, 2023, 2:32pm

Topaz Video AI  v3.2.5
System Information
OS: Mac v13.0301
CPU: Apple M2 Max  96 GB
GPU: Apple M2 Max  72 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	11.45 fps 	2X: 	07.58 fps 	4X: 	02.82 fps 	
Proteus		1X: 	11.23 fps 	2X: 	07.07 fps 	4X: 	02.59 fps 	
Gaia		1X: 	03.37 fps 	2X: 	02.53 fps 	4X: 	01.96 fps 	
4X Slowmo		Apollo: 	09.12 fps 	APFast: 	27.77 fps 	Chronos: 	03.71 fps 	CHFast: 	06.20 fps

Topaz Video AI  v3.2.5
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 3950X 16-Core Processor              31.923 GB
GPU: NVIDIA GeForce RTX 2080 Ti  10.782 GB
GPU: NVIDIA GeForce RTX 2080 Ti  10.782 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	16.82 fps 	2X: 	10.85 fps 	4X: 	03.27 fps 	
Proteus		1X: 	16.59 fps 	2X: 	11.17 fps 	4X: 	03.33 fps 	
Gaia		1X: 	05.36 fps 	2X: 	03.69 fps 	4X: 	02.67 fps 	
4X Slowmo		Apollo: 	07.32 fps 	APFast: 	44.08 fps 	Chronos: 	11.70 fps 	CHFast: 	20.20 fps

Another run on my Win11 machine with only swapping the 2080Ti for a new 3090 (nothing else changed):

Topaz Video AI  v3.2.5
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 3950X 16-Core Processor              31.923 GB
GPU: NVIDIA GeForce RTX 3090  23.77 GB
GPU: NVIDIA GeForce RTX 3090  23.77 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	23.50 fps 	2X: 	13.22 fps 	4X: 	02.95 fps 	
Proteus		1X: 	23.22 fps 	2X: 	12.40 fps 	4X: 	02.89 fps 	
Gaia		1X: 	07.96 fps 	2X: 	05.53 fps 	4X: 	03.48 fps 	
4X Slowmo		Apollo: 	30.41 fps 	APFast: 	40.53 fps 	Chronos: 	18.01 fps 	CHFast: 	25.06 fps

david.123 · May 10, 2023, 3:14pm

I’m running my cpu on 105W eco mode which may explain the difference