Video AI v3.2.X - User Benchmarking Results

[rfrankway]

Topaz Video AI  v3.2.6
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: 	11.26 fps 	2X: 	06.97 fps 	4X: 	02.43 fps 	
Proteus		1X: 	11.86 fps 	2X: 	06.89 fps 	4X: 	02.29 fps 	
Gaia		1X: 	03.38 fps 	2X: 	02.51 fps 	4X: 	01.91 fps 	
4X Slowmo		Apollo: 	09.08 fps 	APFast: 	27.66 fps 	Chronos: 	03.66 fps 	CHFast: 	06.09 fps 	

Same issue on a new Mac…1x is faster…but 2x/4x are slower.

[topaz257 (Michael Karg)]

Here is the explanation from Devs (posted in release thread), for the lower 3.2.6 benchmark results. In short, they made the results more realistic by adding color processing which runs on the CPU. Therefore, most 3.2.6 results can’t be compared to earlier versions.

For users reporting benchmark differences.
Color correction is now part of the benchmarks now. This makes the benchmark results for enhancement models is closer to the actual processing.
Color correction is largely CPU bound and applied on the output, so the performance for 2x and 4x reflects the impact of it more than the 1x on higher end GPUs.
Originally, the benchmarks were designed only to show model performance without encoder/decoder and post processing. This led to differences in benchmark fps and observed fps on machines with slower CPUs or powerful GPUs. This change to benchmark is more inline with the processing times seen by the users.

[longues-poses]

Topaz Video AI  v3.2.6
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 3900X 12-Core Processor              31.924 GB
GPU: AMD Radeon RX 5700 XT  7.9595 GB
Processing Settings
device: 0 vram: 0.91 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	06.26 fps 	2X: 	03.85 fps 	4X: 	01.41 fps 	
Proteus		1X: 	05.93 fps 	2X: 	03.69 fps 	4X: 	01.39 fps 	
Gaia		1X: 	02.98 fps 	2X: 	01.95 fps 	4X: 	01.33 fps 	
4X Slowmo		Apollo: 	07.47 fps 	APFast: 	23.88 fps 	Chronos: 	04.23 fps 	CHFast: 	06.97 fps 	

[longues-poses]

Topaz Video AI Beta  v3.2.6.0.b
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 3900X 12-Core Processor              31.924 GB
GPU: AMD Radeon RX 5700 XT  7.9595 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	06.20 fps 	2X: 	03.81 fps 	4X: 	01.38 fps 	
Proteus		1X: 	05.85 fps 	2X: 	03.71 fps 	4X: 	01.38 fps 	
Gaia		1X: 	02.99 fps 	2X: 	01.98 fps 	4X: 	01.34 fps 	
4X Slowmo		Apollo: 	07.54 fps 	APFast: 	25.57 fps 	Chronos: 	04.24 fps 	CHFast: 	07.00 fps 	

[deveshm]

Topaz Video AI v3.2.6

System Information
OS: Windows v10.2009
CPU: 13th Gen Intel(R) Core(TM) i9-13900K 63.715 GB
GPU: Intel(R) UHD Graphics 770 0.125 GB
GPU: NVIDIA GeForce RTX 3090 23.77 GB
GPU: NVIDIA GeForce RTX 4090 22.096 GB

Processing Settings
device: 2 vram: 1 instances: 0

Input Resolution: 1920x1080

Benchmark Results
Artemis 1X: 33.49 fps 2X: 16.33 fps 4X: 04.33 fps
Proteus 1X: 29.35 fps 2X: 12.67 fps 4X: 04.14 fps
Gaia 1X: 13.24 fps 2X: 09.27 fps 4X: 04.38 fps
4X Slowmo Apollo: 40.34 fps APFast: 79.62 fps Chronos: 28.72 fps CHFast: 32.72 fps

[ShoeStringBudget]

@deveshm

I am using a workflow that uses Chronos and GAIA and while my GPU (4090) is maxed out, my CPU (13900K) is only at around 40% utilization.

It is my understanding that topaz doesn’t support multiple gpus. I wonder if you could successfully run two instances of it (if possible) configured for one job each, with each instance mapped to a distinct GPU. If you had a CPU fast enough to keep up that might be interesting.

edit:

it looks like it sort of works.

ref: Multiple gpu in video ai - Topaz Video AI / General - Topaz Community (topazlabs.com)

[Fredo]

hey, here my benchmark.
do not ask me why it wrote -2 devices…

but i got these results after switching to Auto for prefered devices in preferences
if i let my 4090 selected, i get only 4fps …

Topaz Video AI  v3.2.6
System Information
OS: Windows v11.2009
CPU: 12th Gen Intel(R) Core(TM) i7-12700KF  63.818 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings
device: -2 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	25.84 fps 	2X: 	13.12 fps 	4X: 	03.19 fps 	
Proteus		1X: 	19.72 fps 	2X: 	11.18 fps 	4X: 	02.96 fps 	
Gaia		1X: 	13.80 fps 	2X: 	09.30 fps 	4X: 	03.26 fps 	
4X Slowmo		Apollo: 	33.72 fps 	APFast: 	49.21 fps 	Chronos: 	28.38 fps 	CHFast: 	28.77 fps 	

but in conversion from FHD to 4k,
only this

Proteus, and h265

[david.123 (New Profile Picture!)]

Topaz Video AI  v3.2.6
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: 	36.65 fps 	2X: 	14.07 fps 	4X: 	03.63 fps 	
Proteus		1X: 	31.12 fps 	2X: 	13.22 fps 	4X: 	03.58 fps 	
Gaia		1X: 	15.66 fps 	2X: 	10.77 fps 	4X: 	03.80 fps 	
4X Slowmo		Apollo: 	42.19 fps 	APFast: 	64.28 fps 	Chronos: 	32.09 fps 	CHFast: 	38.26 fps 	

[JesusSheep]

Topaz Video AI  v3.2.6
System Information
OS: Windows v10.2009
CPU: Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz  15.957 GB
GPU: NVIDIA GeForce GTX 1060  5.9014 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 480x360
Benchmark Results
Artemis		1X: 	15.48 fps 	2X: 	09.45 fps 	4X: 	03.54 fps 	
Proteus		1X: 	14.71 fps 	2X: 	08.89 fps 	4X: 	03.38 fps 	
Gaia		1X: 	06.12 fps 	2X: 	04.03 fps 	4X: 	02.69 fps 	
4X Slowmo		Apollo: 	17.75 fps 	APFast: 	64.97 fps 	Chronos: 	09.67 fps 	CHFast: 	15.51 fps 	

[longues-poses]

Topaz Video AI  v3.2.6
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 3900X 12-Core Processor              31.924 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
Processing Settings
device: 0 vram: 0.91 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	18.18 fps 	2X: 	08.90 fps 	4X: 	02.41 fps 	
Proteus		1X: 	17.11 fps 	2X: 	08.95 fps 	4X: 	02.46 fps 	
Gaia		1X: 	06.40 fps 	2X: 	04.43 fps 	4X: 	02.59 fps 	
4X Slowmo		Apollo: 	25.79 fps 	APFast: 	44.92 fps 	Chronos: 	13.78 fps 	CHFast: 	21.51 fps 	

[longues-poses]

Topaz Video AI Beta  v3.2.7.0.b
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 9 3900X 12-Core Processor              31.924 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	18.66 fps 	2X: 	09.11 fps 	4X: 	02.32 fps 	
Proteus		1X: 	16.80 fps 	2X: 	08.68 fps 	4X: 	02.41 fps 	
Gaia		1X: 	06.41 fps 	2X: 	04.42 fps 	4X: 	02.65 fps 	
4X Slowmo		Apollo: 	25.87 fps 	APFast: 	49.05 fps 	Chronos: 	13.81 fps 	CHFast: 	21.24 fps 	

[prescott]

Topaz Video AI  v3.2.7
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: 	26.81 fps 	2X: 	14.42 fps 	4X: 	 03.67 fps 	
Proteus		1X: 	24.14 fps 	2X: 	13.59 fps 	4X: 	 03.84 fps 	
Gaia		1X: 	10.21 fps 	2X: 	07.06 fps 	4X: 	 04.04 fps 	
4X Slowmo	Apollo: 32.42 fps 	APFast:	70.66 fps 	Chronos: 23.14 fps 	CHFast: 	26.30 fps

[reiner (nvidiajetson4christmas)]

Have been away from testing due to my job, but recently had some time to play…

• Win 11, 1950 Threadripper , slow 2400 DR4 RAM, no overclocking / numa tuning, probably the slowest this machine can be tuned…

• A second test I performed prior to this on an i5-3570k showed almost the same resulsts, only slightly slower → CPU and PCIE bandwith are not much of a factor in this scenario

• Two R9 Fury X - 50% power setting (both barely sipping 250 watts together while running) on two PCI-E GEN 3 16x slots. No overclocking whatsoever:

• Manual tweaked TVAI to load FP16 models (instead of the FP32 ones it uses per default).

Topaz Video AI Beta  v3.2.7.0.b
System Information
OS: Windows v11.2009
CPU: AMD Ryzen Threadripper 1950X 16-Core Processor   31.896 GB
GPU: AMD Radeon R9 Fury X Series  3.9749 GB
GPU: AMD Radeon R9 Fury X Series  3.9749 GB
Processing Settings
device: 2 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	05.15 fps 	2X: 	03.33 fps 	4X: 	01.19 fps 	
Proteus		1X: 	05.35 fps 	2X: 	03.38 fps 	4X: 	01.20 fps 	
Gaia		1X: 	02.10 fps 	2X: 	01.38 fps 	4X: 	1.12 fps 	
4X Slowmo	Apollo: 	04.78 fps 	APFast: 	17.58 fps 	Chronos: 	02.81 fps 	CHFast: 	02.45 fps

Topaz Video AI Beta  v3.2.7.0.b
System Information
OS: Windows v11.2009
CPU: AMD Ryzen Threadripper 1950X 16-Core Processor   31.896 GB
GPU: AMD Radeon R9 Fury X Series  3.9749 GB
GPU: AMD Radeon R9 Fury X Series  3.9749 GB
Processing Settings
device: 2 vram: 1 instances: 0
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 	29.48 fps 	2X: 	17.07 fps 	4X: 	05.57 fps 	
Proteus		1X: 	26.80 fps 	2X: 	15.65 fps 	4X: 	05.59 fps 	
Gaia		1X: 	11.62 fps 	2X: 	07.60 fps 	4X: 	05.00 fps 	
4X Slowmo	Apollo: 	23.52 fps 	APFast: 	89.72 fps 	Chronos: 	13.99 fps 	CHFast: 	22.04 fps

[Wombart]

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  v3.2.7
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: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	39.55 fps 	2X: 	19.33 fps 	4X: 	04.70 fps 	
Proteus		1X: 	34.11 fps 	2X: 	16.80 fps 	4X: 	04.68 fps 	
Gaia		1X: 	14.97 fps 	2X: 	10.21 fps 	4X: 	05.05 fps 	
4X Slowmo		Apollo: 	39.21 fps 	APFast: 	77.24 fps 	Chronos: 	30.27 fps 	CHFast: 	33.26 fps 	

[TPX (Thomas D.)]

Hi, could any one with a RTX 4090 benchmark Photo AI?

A Stopwatch would do the job, you just export some images with the new beta normal denoise model, strong sharpen Filter an Enhance Standard enabled.

I just need the times and resolution of the input output images.

That would be really nice.

[CRAY]

Topaz Video AI  v3.2.7
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 7 5700G with Radeon Graphics           63.343 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
GPU: AMD Radeon(TM) Graphics  0.48415 GB
Processing Settings
device: 0 vram: 0.9 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	16.74 fps 	2X: 	08.80 fps 	4X: 	02.34 fps 	
Proteus		1X: 	15.29 fps 	2X: 	08.33 fps 	4X: 	02.28 fps 	
Gaia		1X: 	06.00 fps 	2X: 	04.17 fps 	4X: 	02.48 fps 	
4X Slowmo		Apollo: 	22.93 fps 	APFast: 	42.15 fps 	Chronos: 	12.78 fps 	CHFast: 	19.86 fps 	

[CRAY]

Topaz Video AI Alpha  v3.2.1.3.a
System Information
OS: Windows v11.2009
CPU: AMD Ryzen 7 5700G with Radeon Graphics           63.343 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
GPU: AMD Radeon(TM) Graphics  0.48415 GB
Processing Settings: device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 16.35 fps 	2X: 9.64 fps 	4X: 3.04 fps 	
Proteus		1X: 14.88 fps 	2X: 9.37 fps 	4X: 2.92 fps 	
Gaia		1X: 5.96 fps 	2X: 4.14 fps 	4X: 2.71 fps 	
4X Slowmo		Apollo: 20.47 fps 	Chronos: 12.77 fps 	Chronos Fast: 19.53 fps 	

[ian.freestone (IanF)]

This seems extremely slow compared to the results I am seeing others getting. What one thing could I upgrade on my computer that would make it better?

Topaz Video AI  v3.2.7
System Information
OS: Mac v11.0601
CPU: Intel(R) Core(TM) i9-10910 CPU @ 3.60GHz  32 GB
GPU: AMD Radeon Pro 5700 XT  15.984 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	03.02 fps 	2X: 	02.02 fps 	4X: 	00.78 fps 	
Proteus		1X: 	02.98 fps 	2X: 	02.07 fps 	4X: 	00.87 fps 	
Gaia		1X: 	01.01 fps 	2X: 	00.71 fps 	4X: 	00.55 fps 	
4X Slowmo		Apollo: 	02.57 fps 	APFast: 	09.71 fps 	Chronos: 	  ...    fps 	CHFast: 	   -     fps 	

[godefroydemaupeou-68 (GdM74)]

Topaz Video AI  v3.2.7
System Information
OS: Mac v13.04
CPU: Intel(R) Xeon(R) W-3245 CPU @ 3.20GHz  96 GB
GPU: AMD Radeon Pro W5700X  15.984 GB
GPU: AMD Radeon Pro W5700X  15.984 GB
Processing Settings
device: 2 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	07.33 fps 	2X: 	03.79 fps 	4X: 	01.35 fps 	
Proteus		1X: 	07.67 fps 	2X: 	03.69 fps 	4X: 	01.22 fps 	
Gaia		1X: 	02.65 fps 	2X: 	01.89 fps 	4X: 	01.45 fps 	
4X Slowmo		Apollo: 	03.03 fps 	APFast: 	11.57 fps 	Chronos: 	01.08 fps 	CHFast: 	02.34 fps 	

[godefroydemaupeou-68 (GdM74)]

Topaz Video AI Beta  v3.2.7.0.b
System Information
OS: Mac v13.04
CPU: Intel(R) Xeon(R) W-3245 CPU @ 3.20GHz  96 GB
GPU: AMD Radeon Pro W5700X  15.984 GB
GPU: AMD Radeon Pro W5700X  15.984 GB
Processing Settings
device: 2 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	07.67 fps 	2X: 	03.86 fps 	4X: 	01.39 fps 	
Proteus		1X: 	07.34 fps 	2X: 	03.70 fps 	4X: 	01.25 fps 	
Gaia		1X: 	02.64 fps 	2X: 	01.85 fps 	4X: 	01.49 fps 	
4X Slowmo		Apollo: 	03.18 fps 	APFast: 	11.86 fps 	Chronos: 	01.10 fps 	CHFast: 	02.41 fps