Video AI v3.1.X - User Benchmarking Results

ole.solev · March 19, 2023, 11:55am

Does everyone here always encode FullHD to 4K?
Why not 720x480 or 768x576 (2x is DVD to FullHD)?

kevin.purdy · March 19, 2023, 2:10pm

Not everyone. I upscale to 1080HD almost 100%. Very rare for anything I upscale to go to 4K.

kiprode · March 19, 2023, 2:11pm

Topaz Video AI  v3.1.9
System Information
OS: Mac v11.0704
CPU: Intel(R) Core(TM) i5-9600K CPU @ 3.70GHz  80 GB
GPU: AMD Radeon Pro 580X  8 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 1.65 fps 	2X: 1.07 fps 	4X: 0.42 fps 	
Proteus		1X: 1.69 fps 	2X: 1.16 fps 	4X: 0.49 fps 	
Gaia		1X: 0.57 fps 	2X: 0.4 fps 	4X: 0.31 fps 	
4X Slowmo		Apollo: 1.76 fps 	Chronos: 0.31 fps 	Chronos Fast: 0.58 fps

Topaz Video AI  v3.1.9
System Information
OS: Mac v11.0704
CPU: Intel(R) Core(TM) i5-9600K CPU @ 3.70GHz  80 GB
GPU: AMD Radeon Pro 580X  8 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 9.89 fps 	2X: 6.68 fps 	4X: 2.91 fps 	
Proteus		1X: 10.63 fps 	2X: 6.43 fps 	4X: 2.17 fps 	
Gaia		1X: 3.58 fps 	2X: 2.52 fps 	4X: 1.95 fps 	
4X Slowmo		Apollo: 9.66 fps 	Chronos: 2.24 fps 	Chronos Fast: 4.18 fps

toddsnc · March 19, 2023, 3:01pm

1080p at 50fps then let the player app enlarge to 4K works best for me.

Basio73 · March 20, 2023, 11:14am

Topaz Video AI  v3.1.9
System Information
OS: Windows v11.2009
CPU: 12th Gen Intel(R) Core(TM) i5-12600K  31.783 GB
GPU: NVIDIA GeForce RTX 4070 Ti  11.729 GB
GPU: Intel(R) UHD Graphics 770  0.125 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 103.22 fps 	2X: 42.74 fps 	4X: 10.95 fps 	
Proteus		1X: 82.66 fps 	2X: 40.8 fps 	4X: 11.11 fps 	
Gaia		1X: 48.34 fps 	2X: 30.96 fps 	4X: 17.25 fps 	
4X Slowmo		Apollo: 88.11 fps 	Chronos: 92.72 fps 	Chronos Fast: 123.2 fps

Topaz Video AI  v3.1.9
System Information
OS: Windows v11.2009
CPU: 12th Gen Intel(R) Core(TM) i5-12600K  31.783 GB
GPU: NVIDIA GeForce RTX 4070 Ti  11.729 GB
GPU: Intel(R) UHD Graphics 770  0.125 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 17.92 fps 	2X: 6.99 fps 	4X: 1.93 fps 	
Proteus		1X: 14.21 fps 	2X: 6.65 fps 	4X: 2.06 fps 	
Gaia		1X: 7.79 fps 	2X: 5.21 fps 	4X: 2.77 fps 	
4X Slowmo		Apollo: 19.72 fps 	Chronos: 16.47 fps 	Chronos Fast: 23.24 fps

ForSerious · March 20, 2023, 3:05pm

I never upscale to higher than 1080p. I just post those numbers because that’s what everyone else posted.
If I were to come to this topic, trying to figure out if an AMD RX 6900 XT is worth buying for TVAI, because I found one listed locally for sale. It would be pretty useless if the only person who posted results for one, did it in a different resolution than everyone else. I’m kind of hoping they change it in the next version to avoid that situation, but it’s a good start either way.

JesusSheep · March 20, 2023, 7:39pm

Imac 27"

Topaz Video AI  v3.1.9
System Information
OS: Mac v13.0201
CPU: Intel(R) Core(TM) i5-7600K CPU @ 3.80GHz  32 GB
GPU: AMD Radeon RX 480  8 GB
GPU: AMD Radeon Pro 580  8 GB
Processing Settings: device: 2 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 2.78 fps 	2X: 1.82 fps 	4X: 0.69 fps 	
Proteus		1X: 2.84 fps 	2X: 1.9 fps 	4X: 0.68 fps 	
Gaia		1X: 1.05 fps 	2X: 0.75 fps 	4X: 0.57 fps 	
4X Slowmo		Apollo: 2.21 fps 	Chronos: 0.4 fps 	Chronos Fast: 0.91 fps

Gnz · March 21, 2023, 7:03am

MacBook Pro 2023

Topaz Video AI  v3.1.9
System Information
OS: Mac v13.0201
CPU: Apple M2 Pro  16 GB
GPU: Apple M2 Pro  10.667 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 7.37 fps 	2X: 5.13 fps 	4X: 1.32 fps 	
Proteus		1X: 7.54 fps 	2X: 5.22 fps 	4X: 1.69 fps 	
Gaia		1X: 2.5 fps 	2X: 1.83 fps 	4X: 1.36 fps 	
4X Slowmo		Apollo: 6.18 fps 	Chronos: 2.28 fps 	Chronos Fast: 3.6 fps

lemans99 · March 21, 2023, 8:39am

kinda disappointing …

jonathan.schwabe · March 21, 2023, 11:53am

JesusSheep · March 21, 2023, 8:47pm

@nipun.nath ```
Topaz Video AI v3.1.9
System Information
OS: Mac v13.0201
CPU: Intel(R) Core™ i5-7600K CPU @ 3.80GHz 32 GB
GPU: AMD Radeon RX 480 8 GB
GPU: AMD Radeon Pro 580 8 GB
Processing Settings: device: 2 vram: 1 instances: 1
Input Resolution: 480x360
Benchmark Results
Artemis 1X: 12.65 fps 2X: 8.02 fps 4X: 3.18 fps
Proteus 1X: 12.83 fps 2X: 8.37 fps 4X: 3.28 fps
Gaia 1X: 5.33 fps 2X: 3.86 fps 4X: 2.86 fps
4X Slowmo Apollo: ERR fps Chronos: ERR fps Chronos Fast: ERR fps

Topaz Video AI v3.1.10
System Information
OS: Mac v13.0201
CPU: Intel(R) Core™ i5-7600K CPU @ 3.80GHz 32 GB
GPU: AMD Radeon RX 480 8 GB
GPU: AMD Radeon Pro 580 8 GB
Processing Settings: device: 2 vram: 1 instances: 1
Input Resolution: 480x360
Benchmark Results
Artemis 1X: 12.71 fps 2X: 8.19 fps 4X: 3.23 fps
Proteus 1X: 12.74 fps 2X: 8.15 fps 4X: 3.28 fps
Gaia 1X: 5.39 fps 2X: 3.9 fps 4X: 2.88 fps
4X Slowmo Apollo: ERR fps Chronos: ERR fps Chronos Fast: 3.81 fps

prescott · March 22, 2023, 7:36am

Topaz Video AI  v3.1.10
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: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 23.39 fps 	2X: 9.72 fps 	4X: 2.63 fps 	
Proteus		1X: 18.48 fps 	2X: 9.35 fps 	4X: 2.76 fps 	
Gaia		1X: 10.51 fps 	2X: 6.67 fps 	4X: 3.51 fps 	
4X Slowmo		Apollo: 20.52 fps 	Chronos: 21.67 fps 	Chronos Fast: 25.14 fps

07broom.fibulae · March 23, 2023, 7:21pm

Mac Studio with max vram set to 50% followed by 100%. Note that some results are faster at 50% (sometimes significantly) so its always worth experimenting with vram settings.

Topaz Video AI  v3.1.10
System Information
OS: Mac v13.0201
CPU: Apple M1 Max  32 GB
GPU: Apple M1 Max  21.333 GB
Processing Settings: device: 0 vram: 0.5 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 6.86 fps 	2X: 4.79 fps 	4X: 2.08 fps 	
Proteus		1X: 6.98 fps 	2X: 4.91 fps 	4X: 2.13 fps 	
Gaia		1X: 2.2 fps 	2X: 1.57 fps 	4X: 1.25 fps 	
4X Slowmo	Apollo: 7.46 fps 	Chronos: 2.34 fps 	Chronos Fast: 3.42 fps

Topaz Video AI  v3.1.10
System Information
OS: Mac v13.0201
CPU: Apple M1 Max  32 GB
GPU: Apple M1 Max  21.333 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 7.34 fps 	2X: 4.91 fps 	4X: 1.97 fps 	
Proteus		1X: 6.79 fps 	2X: 4.73 fps 	4X: 1.78 fps 	
Gaia		1X: 2.29 fps 	2X: 1.75 fps 	4X: 1.27 fps 	
4X Slowmo	Apollo: 4.52 fps 	Chronos: 2.34 fps 	Chronos Fast: 3.86 fps

07broom.fibulae · March 23, 2023, 10:59pm

Mac Studio again, this time working with SD input resolution. 10% max vram followed by 100%. Notice that every result is faster when set to 10%…

Topaz Video AI  v3.1.10
System Information
OS: Mac v13.0201
CPU: Apple M1 Max  32 GB
GPU: Apple M1 Max  21.333 GB
Processing Settings: device: 0 vram: 0.1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 33.1 fps 	2X: 22.17 fps 	4X: 8.67 fps 	
Proteus		1X: 33.76 fps 	2X: 23.11 fps 	4X: 8.02 fps 	
Gaia		1X: 10.91 fps 	2X: 7.7 fps 	4X: 6.27 fps 	
4X Slowmo	Apollo: 27.94 fps 	Chronos: 11.68 fps 	Chronos Fast: 15.91 fps

Topaz Video AI  v3.1.10
System Information
OS: Mac v13.0201
CPU: Apple M1 Max  32 GB
GPU: Apple M1 Max  21.333 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 24.16 fps 	2X: 15.38 fps 	4X: 5.62 fps 	
Proteus		1X: 23.72 fps 	2X: 14.44 fps 	4X: 5.07 fps 	
Gaia		1X: 7.69 fps 	2X: 5.79 fps 	4X: 4.66 fps 	
4X Slowmo	Apollo: 27.32 fps 	Chronos: 8.25 fps 	Chronos Fast: 11.19 fps

Imo · March 24, 2023, 7:21am

v.3.1.9 is still the fastest for me. The v.3.2.0.4.a is slightly faster than the v.3.2.0.3.a.

TPX · March 24, 2023, 8:39am

The numbers for the 4090 are sureal (7950X), 40 fps for artemis in the alpha.

Imo · March 24, 2023, 11:47am

v.3.2.0.4.a / the whole windows 11 froze during processing. v.3.1.9 ran rock solid for a whole day whithout any pause.

johnnystar · March 25, 2023, 1:51pm

Mine is the fastest at exactly 0.93 VRAM.

DaveL · March 25, 2023, 5:51pm

Quoted from the releases 3.1.10 thread >>

Topaz Video AI v3.1.10

Hoping to get some more love for AMD, AV1 option still not enabled for 7900 xtx unfortunately. I posted the most relevant benchmarks for the typical all AMD build. Also nice to see that the 7900 xtx perform similar to the RTX 4090

Topaz Video AI  v3.1.10
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 7950X 16-Core Processor              31.146 GB
GPU: AMD Radeon RX 7900 XTX  23.945 GB
GPU: AMD Radeon(TM) Graphics  0.47446 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 640x480
Benchmark Results
Artemis		1X: 65.22 fps 	2X: 23.67 fps 	4X: 7.13 fps 	
Proteus		1X: 43.3 fps 	2X: 24.1 fps 	4X: 8.17 fps 	
Gaia		1X: 47.82 fps 	2X: 33.92 fps 	4X: 18.75 fps 	
4X Slowmo		Apollo: 119.97 fps 	Chronos: 43.39 fps 	Chronos Fast: 78.8 fps

XTX stats are excellent for the price, but are closer to (but better than) the RTX 3060 TI actually, which is of course well under half the XTX price and around 25% of the 4090 price. At SD resolutions, my benchmarks for the 3060 TI are mostly faster than the XTX. I’m now off to find some SD benchmarks posted for the 4090

The odd thing is that there are wild variations between some of the models’ performances - my 3060 TI performs badly on Gaia and one or two others, but mostly very well.

Topaz Video AI v3.1.10
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 7 5800X 8-Core Processor 31.948 GB
GPU: NVIDIA GeForce RTX 3060 Ti 7.8496 GB
Processing Settings: device: -2 vram: 0.99 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 10.73 fps 2X: 5.73 fps 4X: 1.56 fps
Proteus 1X: 9.21 fps 2X: 5.2 fps 4X: 1.53 fps
Gaia 1X: 4.05 fps 2X: 2.48 fps 4X: 1.65 fps
4X Slowmo Apollo: 12.23 fps Chronos: 8.61 fps Chronos Fast: 11.08 fps

Topaz Video AI v3.1.10
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 7 5800X 8-Core Processor 31.948 GB
GPU: NVIDIA GeForce RTX 3060 Ti 7.8496 GB
Processing Settings: device: -2 vram: 0.99 instances: 1
Input Resolution: 640x480
Benchmark Results
Artemis 1X: 60.73 fps 2X: 28.07 fps 4X: 9.02 fps
Proteus 1X: 53.79 fps 2X: 25.98 fps 4X: 8.69 fps
Gaia 1X: 23.7 fps 2X: 15.88 fps 4X: 9.99 fps
4X Slowmo Apollo: 72.99 fps Chronos: 45.99 fps Chronos Fast: 59.19 fps

The law of diminishing returns certainly applies here for me, because I use Artemis or Proteus for 2x upscales and Apollo or Chronos Fast for slomo. And if I upgrade the GPU in my existing no. 2 PC to a 3060 TI (making 2 systems with 3060 TI), I can get more throughput at 1080p or below than a single 4090, for 25% of the price of a single 4090 upgrade.

These benchmark tables are a brilliant help in choosing what to do!

stephane.auger · March 26, 2023, 8:33am

Hello there,

My benchmark results

Topaz Video AI v3.1.10
System Information
OS: Windows v11.2009
CPU: 12th Gen Intel(R) Core™ i7-12700K 31.789 GB
GPU: NVIDIA GeForce RTX 3070 Ti 7.8428 GB
GPU: Intel(R) UHD Graphics 770 0.125 GB
Processing Settings: device: 0 vram: 1 instances: 1

Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 11.49 fps 2X: 5.04 fps 4X: 1.42 fps
Proteus 1X: 8.9 fps 2X: 4.79 fps 4X: 1.39 fps
Gaia 1X: 5.11 fps 2X: 3.3 fps 4X: 1.83 fps
4X Slowmo Apollo: 13.38 fps Chronos: 10.83 fps Chronos Fast: 15.26 fps

Input Resolution: 720x480
Benchmark Results
Artemis 1X: 77.4 fps 2X: 33.48 fps 4X: 8.1 fps
Proteus 1X: 63.65 fps 2X: 27.65 fps 4X: 8.18 fps
Gaia 1X: 28.77 fps 2X: 19.81 fps 4X: 11.41 fps
4X Slowmo Apollo: 74.74 fps Chronos: 56.27 fps Chronos Fast: 75.02 fps

Input Resolution: 640x480
Benchmark Results
Artemis 1X: 80.19 fps 2X: 31.05 fps 4X: 8.37 fps
Proteus 1X: 62.72 fps 2X: 27.94 fps 4X: 7.95 fps
Gaia 1X: 29.05 fps 2X: 20.19 fps 4X: 11.76 fps
4X Slowmo Apollo: 72.93 fps Chronos: 57.39 fps Chronos Fast: 73.1 fps