Video AI v3.2.X - User Benchmarking Results

Starting from Topaz Video AI v3.1.9, users can run benchmarking (Process > Benchmark, or, Ctrl/Cmd + B) to compare results across different machines. This option doesn’t transmit any data and is completely up to the user to share. Once benchmarking is finished you can copy and paste the results here.


3.2.0

Topaz Video AI  v3.2.0
System Information
OS: Windows v11.2009
CPU: Intel(R) Core(TM) i9-10900KF CPU @ 3.70GHz  31.939 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: 19.06 fps 	2X: 10.84 fps 	4X: 3.59 fps 	
Proteus		1X: 16.88 fps 	2X: 8.39 fps 	4X: 3.09 fps 	
Gaia		1X: 7.03 fps 	2X: 4.87 fps 	4X: 3.16 fps 	
4X Slowmo		Apollo: 21.27 fps 	Chronos: 15.78 fps 	Chronos Fast: 20.58 fps 	

3.1.11

Topaz Video AI  v3.1.11
System Information
OS: Windows v11.2009
CPU: Intel(R) Core(TM) i9-10900KF CPU @ 3.70GHz  31.939 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: 14.17 fps 	2X: 5.45 fps 	4X: 1.45 fps 	
Proteus		1X: 10.68 fps 	2X: 4.84 fps 	4X: 1.46 fps 	
Gaia		1X: 6.78 fps 	2X: 4.42 fps 	4X: 2.27 fps 	
4X Slowmo		Apollo: 14.95 fps 	Chronos: 14.56 fps 	Chronos Fast: 20.29 fps 	


Please use this thread to share benchmark results for 3.2.x releases. Thank you.

1 Like

Topaz Video AI v3.2.0
System Information
OS: Windows v10.2009
CPU: Intel(R) Core™ i7-4770K CPU @ 3.50GHz 31.877 GB
GPU: NVIDIA GeForce RTX 2080 7.8145 GB
GPU: Intel(R) HD Graphics 4600 0.10986 GB
Processing Settings: device: -2 vram: 0.9 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 11.33 fps 2X: 7.47 fps 4X: 2.07 fps
Proteus 1X: 11.49 fps 2X: 6.49 fps 4X: 1.97 fps
Gaia 1X: 3.74 fps 2X: 2.52 fps 4X: 1.76 fps
4X Slowmo Apollo: 13.71 fps Chronos: 3.58 fps Chronos Fast: 12.84 fps

Topaz Video AI  v3.2.0
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 5900X 12-Core Processor              31.929 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: 22.55 fps 	2X: 13.20 fps 	4X: 3.46 fps 	
Proteus		1X: 19.79 fps 	2X: 12.20 fps 	4X: 3.26 fps 	
Gaia		1X: 8.06 fps 	2X: 5.54 fps 	4X: 3.27 fps 	
4X Slowmo		Apollo: 23.15 fps 	Chronos: 17.53 fps 	Chronos Fast: 25.90 fps 	

Fresh reboot (waited for everything to settle down), no other tasks running and Run1 is first pass at benchmarks, then Run2 is right after that to see if there is any caching effect. Fresh run on 3.1.11 before updating to compare with. :+1:

3.1.11 (fresh reboot):

Run1:

Topaz Video AI  v3.1.11
System Information
OS: Mac v13.03
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: 10.42 fps 	2X: 7.42 fps 	4X: 2.64 fps 	
Proteus		1X: 10.83 fps 	2X: 7.43 fps 	4X: 2.19 fps 	
Gaia		1X: 3.39 fps 	2X: 2.52 fps 	4X: 1.9 fps 	
4X Slowmo		Apollo: 11.19 fps 	Chronos: 3.31 fps 	Chronos Fast: 5.3 fps 	

Run2:

Topaz Video AI  v3.1.11
System Information
OS: Mac v13.03
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: 11.06 fps 	2X: 7.34 fps 	4X: 2.5 fps 	
Proteus		1X: 10.89 fps 	2X: 7.01 fps 	4X: 2.36 fps 	
Gaia		1X: 3.28 fps 	2X: 2.36 fps 	4X: 1.71 fps 	
4X Slowmo		Apollo: 10.57 fps 	Chronos: 3.34 fps 	Chronos Fast: 5.29 fps 	

3.2.0 (fresh reboot):

Run1:

Topaz Video AI  v3.2.0
System Information
OS: Mac v13.03
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: 10.56 fps 	2X: 7.64 fps 	4X: 2.90 fps 	
Proteus		1X: 11.26 fps 	2X: 7.29 fps 	4X: 2.50 fps 	
Gaia		1X: 3.34 fps 	2X: 2.44 fps 	4X: 1.88 fps 	
4X Slowmo		Apollo: 9.89 fps 	Chronos: 3.76 fps 	Chronos Fast: 6.22 fps 	

Run2:

Topaz Video AI  v3.2.0
System Information
OS: Mac v13.03
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: 10.69 fps 	2X: 7.37 fps 	4X: 2.90 fps 	
Proteus		1X: 11.05 fps 	2X: 7.34 fps 	4X: 2.46 fps 	
Gaia		1X: 3.31 fps 	2X: 2.29 fps 	4X: 1.71 fps 	
4X Slowmo		Apollo: 9.08 fps 	Chronos: 3.59 fps 	Chronos Fast: 5.99 fps 	

1 Like
Topaz Video AI  v3.2.0
System Information
OS: Windows v11.2009
CPU: Intel(R) Core(TM) i9-10900K CPU @ 3.70GHz  31.843 GB
GPU: AMD Radeon RX 7900 XT  19.945 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 11.82 fps 	2X: 5.35 fps 	4X: 1.57 fps 	
Proteus		1X: 9.76 fps 	2X: 4.83 fps 	4X: 1.54 fps 	
Gaia		1X: 7.56 fps 	2X: 4.84 fps 	4X: 2.01 fps 	
4X Slowmo		Apollo: 15.25 fps 	Chronos: 9.04 fps 	Chronos Fast: 14.30 fps 	

Topaz Video AI v3.1.11
System Information
OS: Windows v11.2009
CPU: Intel(R) Core™ i9-10900K CPU @ 3.70GHz 31.843 GB
GPU: AMD Radeon RX 7900 XT 19.945 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 8.18 fps 2X: 3.25 fps 4X: 0.92 fps
Proteus 1X: 5.76 fps 2X: 2.75 fps 4X: 0.89 fps
Gaia 1X: 7.76 fps 2X: 3.38 fps 4X: 1.67 fps
4X Slowmo Apollo: 13 fps Chronos: 6.49 fps Chronos Fast: 7.55 fps

FHD, HD and NTSC before and after updating:

FHD:

Topaz Video AI  v3.1.11
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core(TM) i9-13900KF  63.816 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 31.15 fps 	2X: 13.1 fps 	4X: 3.51 fps 	
Proteus		1X: 25.32 fps 	2X: 11.63 fps 	4X: 3.59 fps 	
Gaia		1X: 14.94 fps 	2X: 9.7 fps 	4X: 4.63 fps 	
4X Slowmo		Apollo: 27.06 fps 	Chronos: 28.74 fps 	Chronos Fast: 34.68 fps 	

Topaz Video AI  v3.2.0
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core(TM) i9-13900KF  63.816 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings: device: 0 vram: 0.9 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 40.11 fps 	2X: 21.69 fps 	4X: 6.44 fps 	
Proteus		1X: 36.48 fps 	2X: 20.64 fps 	4X: 6.33 fps 	
Gaia		1X: 15.16 fps 	2X: 10.40 fps 	4X: 6.48 fps 	
4X Slowmo		Apollo: 37.08 fps 	Chronos: 32.72 fps 	Chronos Fast: 33.53 fps 	

HD:

Topaz Video AI  v3.1.11
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core(TM) i9-13900KF  63.816 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1280x720
Benchmark Results
Artemis		1X: 76.44 fps 	2X: 30.3 fps 	4X: 8 fps 	
Proteus		1X: 58.61 fps 	2X: 28.45 fps 	4X: 8.05 fps 	
Gaia		1X: 33.71 fps 	2X: 21.03 fps 	4X: 10.14 fps 	
4X Slowmo		Apollo: 57.08 fps 	Chronos: 66.7 fps 	Chronos Fast: 78.13 fps 	

Topaz Video AI  v3.2.0
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core(TM) i9-13900KF  63.816 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings: device: 0 vram: 0.9 instances: 0
Input Resolution: 1280x720
Benchmark Results
Artemis		1X: 86.17 fps 	2X: 50.13 fps 	4X: 14.76 fps 	
Proteus		1X: 77.75 fps 	2X: 44.16 fps 	4X: 13.34 fps 	
Gaia		1X: 34.11 fps 	2X: 23.35 fps 	4X: 14.52 fps 	
4X Slowmo		Apollo: 76.24 fps 	Chronos: 71.51 fps 	Chronos Fast: 84.24 fps 	

NTSC:

Topaz Video AI  v3.1.11
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core(TM) i9-13900KF  63.816 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 174.23 fps 	2X: 67.88 fps 	4X: 16.92 fps 	
Proteus		1X: 128.43 fps 	2X: 65.18 fps 	4X: 17.03 fps 	
Gaia		1X: 84.68 fps 	2X: 56.71 fps 	4X: 28.69 fps 	
4X Slowmo		Apollo: 124.89 fps 	Chronos: 130.15 fps 	Chronos Fast: 123.96 fps 	

Topaz Video AI  v3.2.0
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core(TM) i9-13900KF  63.816 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings: device: 0 vram: 0.9 instances: 0
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 208.46 fps 	2X: 100.06 fps 	4X: 29.70 fps 	
Proteus		1X: 154.24 fps 	2X: 83.03 fps 	4X: 28.47 fps 	
Gaia		1X: 84.04 fps 	2X: 59.24 fps 	4X: 34.92 fps 	
4X Slowmo		Apollo: 213.73 fps 	Chronos: 161.44 fps 	Chronos Fast: 208.44 fps 	

All hardware components at stock settings, no OC.

(Edit: regrouped results by resolution for easier comparison.)

I know this is not a feature request forum, but going to put this out here anyway: A timestamp field in the results would be useful. Local or UTC, good either way.

2 Likes
Topaz Video AI  v3.2.0
System Information
OS: Windows v10.2009
CPU:        Intel(R) Core(TM) i5-2500K CPU @ 4.70GHz  15.971 GB
GPU: NVIDIA GeForce RTX 3060  11.845 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 8.78 fps 2X: 7.49 fps 4X: 1.92 fps
Proteus 1X: 11.52 fps 2X: 6.85 fps 4X: 1.80 fps
Gaia 1X: 3.20 fps 2X: 2.14 fps 4X: 1.32 fps
4X Slowmo Apollo: 12.67 fps Chronos: 7.38 fps Chronos Fast: 12.76 fps

Theoretical its more then twice faster then v3.1.9 - which is very good work ! But …
I decided to make “real life” test and the results unfortunately are pretty disturbing :frowning:
By the benchmark i get about 30fps for 640x480p input upscaled 2X by Proteus ! But when i try to upscale real 640x480p@29.97fps vid 2X by Proteus (no other enhancements enabled) it takes about 4 minutes for 1 minute of the original vid . Or this is about 4 times slower then the data from the benchmark !!!
So my question is - is this some kind of bug or this is just a SCAM benchmark info to mislead the users that there is really great improvement in the newer Topaz software ?
Everybody can make such “real life” test for himself and compare with the benchmark info ! Will be nice to hear about other users experience . So please share it here!

One Radeon card is installed, but TVAI looks like dual cards.

Topaz Video AI v3.2.0
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 5 5600X 6-Core Processor 31.917 GB
GPU: AMD Radeon RX 6750 XT 11.955 GB
GPU: AMD Radeon RX 6750 XT 11.955 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 8.31 fps 2X: 4.64 fps 4X: 1.65 fps
Proteus 1X: 7.66 fps 2X: 4.59 fps 4X: 1.61 fps
Gaia 1X: 4.02 fps 2X: 2.69 fps 4X: 1.76 fps
4X Slowmo Apollo: 9.73 fps Chronos: 5.60 fps Chronos Fast: 9.34 fps

Topaz Video AI v3.1.11
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 5 5600X 6-Core Processor 31.917 GB
GPU: AMD Radeon RX 6750 XT 11.955 GB
GPU: AMD Radeon RX 6750 XT 11.955 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 3.42 fps 2X: 1.96 fps 4X: 0.77 fps
Proteus 1X: 3.05 fps 2X: 1.85 fps 4X: 0.74 fps
Gaia 1X: 2.99 fps 2X: 1.91 fps 4X: 1.24 fps
4X Slowmo Apollo: 8.12 fps Chronos: 4.12 fps Chronos Fast: 5.65 fps

I think the benchmark either writes the output to RAM or just ignores it. This can make a huge difference on speed. In the tests I’ve done before, using NVENC slows things down compared to PNG output. PNG output on a slow HDD goes fast until the cache gets filled, then the whole thing slows down to a crawl. I have SSDs that work the same way, but slow down even more once the cache is filled.

So yes. The speeds will not be the same. Benchmarks should try to eliminate as many extra variables as they can to test only the hardware in question. I believe they have removed the encoding impact from this benchmark.

This is because you either have dual/head monitors or a thunderbolt port expander going to two monitors. It is only using one (device 0).

You cannot compare like this. The video content and encoding is likely very different (10-bit vs. 8-bit, busy content like water scene vs. mostly still, the codec involved, fps, etc.). The only way to compare is to run the same real video on 3.1.x vs 3.2.0. What is that result? The world is not out to get you.

Wow. Pretty impressive improvement from 3.1.11 to 3.2.0!
Results for both below with percentage improvement at bottom:

Topaz Video AI v3.1.11
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core™ i9-13900K 127.77 GB
GPU: NVIDIA GeForce RTX 3090 Ti 23.757 GB
GPU: Intel(R) UHD Graphics 770 0.125 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 20.67 fps 2X: 9.22 fps 4X: 2.47 fps
Proteus 1X: 16.27 fps 2X: 8.26 fps 4X: 2.57 fps
Gaia 1X: 8.75 fps 2X: 5.71 fps 4X: 3.17 fps
4X Slowmo Apollo: 20.49 fps Chronos: 17.83 fps Chronos Fast: 27.84 fps

Topaz Video AI v3.2.0
System Information
OS: Windows v11.2009
CPU: 13th Gen Intel(R) Core™ i9-13900K 127.77 GB
GPU: NVIDIA GeForce RTX 3090 Ti 23.757 GB
GPU: Intel(R) UHD Graphics 770 0.125 GB
Processing Settings: device: 0 vram: 0.9 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 25.28 fps 2X: 16.17 fps 4X: 4.75 fps
Proteus 1X: 24.73 fps 2X: 14.73 fps 4X: 4.25 fps
Gaia 1X: 9.01 fps 2X: 6.09 fps 4X: 3.79 fps
4X Slowmo Apollo: 32.83 fps Chronos: 19.82 fps Chronos Fast: 26.66 fps


Artemis		22%			75%			92%
Proteus		52%			78%			65%
Gaia			3%			7%			20%
4X Slowmo		60%			11%			-1%
Topaz Video AI  v3.1.11
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 9 5950X 16-Core Processor              31.915 GB
GPU: NVIDIA GeForce RTX 3080  9.8311 GB
GPU: NVIDIA GeForce RTX 3080  9.8311 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 14.49 fps 	2X: 6.4 fps 	4X: 1.84 fps 	
Proteus		1X: 11.75 fps 	2X: 5.97 fps 	4X: 1.82 fps 	
Gaia		1X: 5.71 fps 	2X: 3.79 fps 	4X: 2.09 fps 	
4X Slowmo		Apollo: 16.6 fps 	Chronos: 12.16 fps 	Chronos Fast: 18.1 fps 	

Topaz Video AI  v3.2.0
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 9 5950X 16-Core Processor              31.915 GB
GPU: NVIDIA GeForce RTX 3080  9.8311 GB
GPU: NVIDIA GeForce RTX 3080  9.8311 GB
Processing Settings: device: 0 vram: 0.9 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 19.94 fps 	2X: 13.33 fps 	4X: 3.54 fps 	
Proteus		1X: 20.89 fps 	2X: 12.29 fps 	4X: 3.31 fps 	
Gaia		1X: 6.64 fps 	2X: 4.66 fps 	4X: 3.19 fps 	
4X Slowmo		Apollo: 21.94 fps 	Chronos: 14.69 fps 	Chronos Fast: 22.54 fps 	

Proteus 2X: 20.64 fps At first looks like nice performance but i believe Topaz isnt yet good optimized for RTX 4xxx series … My RTX 3060 get Proteus 2X: 6.80 fps which is about just 3 times slower (even at 11 years old i5-2500K) . Tensor compute power of the 3060 is 51.2 TFLOPS while this of 4090 is 330.3 TFLOPS which is more then 6 times higher … So my point is that if the software is really good optimized to use the full power of 4090 the Proteus performance has to be about twice higher or about 40fps …
Also from 3090Ti results above get Proteus 2X: 14.73 fps (which seems logically compared to 3060) but the tensor compute power of the 3090Ti is just the half of 4090 or its just 160 TFLOPS My point is thats not realistic 3090Ti performance to be so close to 4090 at very same CPU and OS …

Topaz Video AI  v3.2.0
System Information
OS: Windows v10.2009
CPU: Intel(R) Core(TM) i7-6950X CPU @ 3.00GHz  31.925 GB
GPU: NVIDIA GeForce RTX 4080  15.688 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 27.46 fps 	2X: 17.28 fps 	4X: 4.69 fps 	
Proteus		1X: 23.96 fps 	2X: 15.50 fps 	4X: 4.55 fps 	
Gaia		1X: 10.37 fps 	2X: 7.07 fps 	4X: 4.45 fps 	
4X Slowmo		Apollo: 25.69 fps 	Chronos: 23.10 fps 	Chronos Fast: 25.07 fps 	

Just because I feel like showing off a little here’s mine :grin:

Topaz Video AI  v3.2.0
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: 42.34 fps 	2X: 19.27 fps 	4X: 3.60 fps 	
Proteus		1X: 33.63 fps 	2X: 18.00 fps 	4X: 3.54 fps 	
Gaia		1X: 15.67 fps 	2X: 10.83 fps 	4X: 4.93 fps 	
4X Slowmo		Apollo: 29.53 fps 	Chronos: 31.91 fps 	Chronos Fast: 38.21 fps 	

Interesting my 3090 Ti has some areas it is ahead in

Topaz Video AI  v3.2.0
System Information
OS: Windows v11.2009
CPU: 12th Gen Intel(R) Core(TM) i9-12900KS  31.278 GB
GPU: NVIDIA GeForce RTX 3090 Ti  23.757 GB
GPU: Intel(R) UHD Graphics 770  0.125 GB
Processing Settings: device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 25.78 fps 	2X: 16.85 fps 	4X: 5.03 fps 	
Proteus		1X: 24.93 fps 	2X: 16.34 fps 	4X: 5.11 fps 	
Gaia		1X: 9.09 fps 	2X: 6.15 fps 	4X: 3.78 fps 	
4X Slowmo		Apollo: 33.00 fps 	Chronos: 20.15 fps 	Chronos Fast: 27.23 fps 	

2 Likes