Video AI 6.0.X - User Benchmarking Results

Overclocked gpu or cpu? Gpu load behaves very different when ai rendering. Stable clock on gpu for me while rendering is some 10% lower than in any other gpu environment/benchmark over the last 2 years.

Topaz Video AI  v6.0.1
System Information
OS: Mac v14.0201
CPU: Intel(R) Core(TM) i9-9980HK CPU @ 2.40GHz  64 GB
GPU: AMD Radeon Pro 5600M  7.9844 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	02.26 fps 	2X: 	01.46 fps 	4X: 	00.49 fps 	
Iris		1X: 	01.40 fps 	2X: 	00.78 fps 	4X: 	00.22 fps 	
Proteus		1X: 	01.61 fps 	2X: 	00.91 fps 	4X: 	00.32 fps 	
Gaia		1X: 	00.23 fps 	2X: 	00.20 fps 	4X: 	00.21 fps 	
Nyx		1X: 	00.46 fps 	2X: 	00.45 fps 	
Nyx Fast		1X: 	01.29 fps 	
Rhea		4X: 	00.21 fps 	
RXL		4X: 	00.22 fps 	
Hyperion HDR		1X: 	27.01 fps 	
4X Slowmo		Apollo: 	01.19 fps 	APFast: 	05.53 fps 	Chronos: 	00.28 fps 	CHFast: 	00.71 fps 	
16X Slowmo		Aion: 	01.16 fps 	

Topaz Video AI  v6.0.1
System Information
OS: Mac v15.02
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: 	08.27 fps 	2X: 	05.24 fps 	4X: 	01.21 fps 	
Iris		1X: 	05.44 fps 	2X: 	03.23 fps 	4X: 	00.72 fps 	
Proteus		1X: 	07.25 fps 	2X: 	04.23 fps 	4X: 	01.19 fps 	
Gaia		1X: 	02.15 fps 	2X: 	01.46 fps 	4X: 	01.02 fps 	
Nyx		1X: 	02.03 fps 	2X: 	02.10 fps 	
Nyx Fast		1X: 	07.76 fps 	
Rhea		4X: 	00.59 fps 	
RXL		4X: 	00.58 fps 	
Hyperion HDR		1X: 	33.96 fps 	
4X Slowmo		Apollo: 	08.53 fps 	APFast: 	38.31 fps 	Chronos: 	02.51 fps 	CHFast: 	04.57 fps 	
16X Slowmo		Aion: 	10.37 fps 	

Topaz Video AI  v6.0.2
System Information
OS: Windows v11.24
CPU: 12th Gen Intel(R) Core(TM) i5-12600K  15.775 GB
GPU: NVIDIA GeForce RTX 4060 Ti  7.7627 GB
Processing Settings
device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	13.50 fps 	2X: 	08.94 fps 	4X: 	02.63 fps 	
Iris		1X: 	14.51 fps 	2X: 	08.37 fps 	4X: 	02.12 fps 	
Proteus		1X: 	13.09 fps 	2X: 	08.74 fps 	4X: 	02.91 fps 	
Gaia		1X: 	04.41 fps 	2X: 	03.08 fps 	4X: 	02.03 fps 	
Nyx		1X: 	05.17 fps 	2X: 	04.50 fps 	
Nyx Fast		1X: 	09.01 fps 	
Rhea		4X: 	01.70 fps 	
RXL		4X: 	01.50 fps 	
Hyperion HDR		1X: 	22.67 fps 	
4X Slowmo		Apollo: 	19.59 fps 	APFast: 	53.18 fps 	Chronos: 	10.51 fps 	CHFast: 	16.04 fps 	
16X Slowmo		Aion: 	20.26 fps 	

Forget RAM 16GB DDR4 3200, very good machine, far from the highest end beasts here.

1 Like

I have not gotten any heads up on this that is locked into a timeline at this point.

Topaz Video AI  v6.0.1
System Information
OS: Windows v11.23
CPU: AMD Ryzen 7 7800X3D 8-Core Processor             63.117 GB
GPU: AMD Radeon RX 7900 XTX  23.924 GB
GPU: AMD Radeon(TM) Graphics  0.45682 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	21.39 fps 	2X: 	13.21 fps 	4X: 	04.21 fps 	
Iris		1X: 	24.67 fps 	2X: 	14.62 fps 	4X: 	05.05 fps 	
Proteus		1X: 	24.32 fps 	2X: 	16.55 fps 	4X: 	04.90 fps 	
Gaia		1X: 	09.93 fps 	2X: 	06.73 fps 	4X: 	04.47 fps 	
Nyx		1X: 	10.06 fps 	2X: 	08.22 fps 	
Nyx Fast		1X: 	19.68 fps 	
Rhea		4X: 	02.92 fps 	
RXL		4X: 	02.82 fps 	
Hyperion HDR		1X: 	27.49 fps 	
4X Slowmo		Apollo: 	32.01 fps 	APFast: 	76.32 fps 	Chronos: 	16.17 fps 	CHFast: 	25.41 fps 	
16X Slowmo		Aion: 	30.69 fps 	

Topaz Video AI Beta  v6.0.2.1
System Information
OS: Mac v15.03
CPU: Apple M2 Ultra  64 GB
GPU: Apple M2 Ultra  48 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	15.33 fps 	2X: 	08.31 fps 	4X: 	03.05 fps 	
Iris		1X: 	09.96 fps 	2X: 	04.71 fps 	4X: 	02.34 fps 	
Proteus		1X: 	15.36 fps 	2X: 	09.46 fps 	4X: 	03.31 fps 	
Gaia		1X: 	06.13 fps 	2X: 	04.13 fps 	4X: 	02.73 fps 	
Nyx		1X: 	04.08 fps 	2X: 	04.34 fps 	
Nyx Fast		1X: 	13.13 fps 	
Rhea		4X: 	01.40 fps 	
RXL		4X: 	01.44 fps 	
Hyperion HDR		1X: 	46.95 fps 	
4X Slowmo		Apollo: 	19.53 fps 	APFast: 	74.78 fps 	Chronos: 	05.93 fps 	CHFast: 	07.55 fps 	
16X Slowmo		Aion: 	17.34 fps 	

Still abysmal Iris performanceon Apple Silicon, now even for 1x.

These numbers seemed low until I saw your input was already in 4k :slight_smile:

Hopefully this post is appreciated and in the preferred location within the community. I’m putting this post here as it’s the only place I’m seeing benchmark comparisons. I have tried nearly everything I can to get an Apple computer (MacBook, Mac mini, Mac Studio) to work well with the Topaz suites. Below are some lessons learned that hopefully can help those trying to match a computer to the software while staying in the MacOS environment. First the computer specs, then the insights:

Computers Tested:

#1: Macbook M1, 8 CPU, 14 GPU, 16 GB RAM, 512 GB SSD
#2: Mac Mini M4, 10 CPU, 10 GPU, 16 GB RAM, 512 GB SSD
#3, Mac Mini M4 Pro, 12 CPU, 16 GPU, 24 GB RAM, 1 TB SSD
#4: Mac Studio M1 Ultra, 20 CPU, 64 GPU, 128 GB RAM, 2 TB SSD
#5: Macbook M4 Max 14 Inch, 14 CPU, 32 GPU, 36 GB RAM, 1 TB SSD
#6: Macbook M4 Max 14 Inch, 16 CPU, 40 GPU, 64 GB RAM, 1 TB SSD

I also tested my brother’s laptop with a NVIDIA 3070 GPU (other specs not known). It crushed the first 3 tested and beat out the last 3 (4 through 6).

Overall:

I’ve listed the computers in order of performance with #6 being the highest performance specifically to my experience in the 3 Topaz products. Move down the line to increase performance.

Running Video AI, Generative models in Gigapixel, or Superfocus Beta in Photo AI will max out the GPUs on every computer listed.

Every computer consistently ran into issues with Topaz software. Most of the issues documented on this site were ones I experienced (force quitting, ā€œfilm negativeā€ rendering, non rendering, B&W rendering, etc.). I’ve concluded that Topaz simply isn’t a ā€œstableā€ product on Macs. I regularly uninstalled and reinstalled apps, removed cached folders and files, and installed older versions of the software as temporary solutions to the consistent problems. The problems keep coming back after consistent use.

The capability of the software is phenomenal, and to me, worth the money spent even with the consistent issues had. Move to a PC if you’re not okay with the bugginess.

Computer Insights:

M1 vs M4 Chip: the M1 struggles even on the M1 Studio. However, the M1 studio did far better than M1 MacBook. If choosing between M1 Studio and M4 Pro, they were near equals. I’d recommend going with the M4 Pro over the M1 studio based on my experience. If I had to guess, I’d guess the M4 chip holding other things equal is 2x the performance of an M1 chip in Topaz.

M4 Macbook vs M4 Mac Mini: I did not notice a performance difference.

M4 vs M4 Pro vs M4 Max Chip: any differences identified had to do with the GPU based on my user experience.

CPU: Honestly, I never noticed CPU being an issue even at 8 CPU.

GPU: Other things held equal, 25% more cores will give you 25% more efficient render times. When purchasing a Mac, simply evaluate if the extra cores as a percent increase is worth the additional money and time savings. 20 to 40 cores would double your speed for example but don’t forget that the chip matters.

RAM: When working in a single Topaz program, there is very little benefit to purchase RAM above 48 GB but there were notable gains up to 48. When working in 2+ programs (I often render in Gigapixel and Video AI at the same time), 64 GB RAM is very helpful but additional RAM did nothing for performance.

SSD: you do not want your SSD near full for smooth operation, especially if you skimp on RAM. Be sure to allow for 25% free space at 512 GB or 1 TB, 15% at 2 TB to ensure this doesn’t impact performance.

Power Management: When running the two M4 Max MacBooks side-by-side, I accidentally learned that the 32 GPU 36 GB Ram option in high power mode was nearly identical to the 40 GPU 64 GP RAM option when in normal power mode. Putting the 40 GPU computer in high power mode effectively boosted performance by 20%.

Topaz Insights:

Topaz Gigapixel: When working with the Basic Models in Gigapixel, all computers tested were up to the task but most consistently had issues in the Generative Models. The M1 MacBook struggled too much for my satisfaction on even basic models.
I tested my brother’s laptop with a NVIDIA 3070 and it was faster than every Mac option I tested and by a fair margin. If you want to use Topaz in near-real-time, no Mac will give you this joy today; go the PC route.

Topaz Photo AI: With the exception of SuperFocus Beta, all computers got the job done with increasing performance as you moved from #1 through #6 computer. For Super Focus Beta, all computers are SLOW; get a NVIDIA GPU if you want image renders faster than every 10-20 minutes (based on roughly 1k x 2k photo with 2x upscaling).

Topaz Video AI: It’s all about the GPUs baby! Frame rate production appears to be a linear relationship to the number of GPUs, holding other things constant.

Topaz is a great product with poor buggy performance on Macs today when doing anything beyond the basic models. It’s worth the money to me though and I appreciate the solution Topaz has brought to the market. I’ve tested other software solutions for both photo and video rendering and find Topaz to be the best when it works.

4 Likes
Topaz Video AI  v6.0.2
System Information
OS: Windows v11.24
CPU: Intel(R) Xeon(R) w5-2465X  127.25 GB
GPU: NVIDIA GeForce RTX 4070  11.73 GB
GPU: NVIDIA RTX A4000  15.79 GB
Processing Settings
device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	18.58 fps 	2X: 	12.31 fps 	4X: 	03.54 fps 	
Iris		1X: 	18.80 fps 	2X: 	11.51 fps 	4X: 	03.24 fps 	
Proteus		1X: 	17.72 fps 	2X: 	12.27 fps 	4X: 	04.02 fps 	
Gaia		1X: 	06.13 fps 	2X: 	04.24 fps 	4X: 	02.89 fps 	
Nyx		1X: 	07.25 fps 	2X: 	06.17 fps 	
Nyx Fast		1X: 	13.40 fps 	
Rhea		4X: 	02.36 fps 	
RXL		4X: 	02.12 fps 	
Hyperion HDR		1X: 	07.98 fps 	
4X Slowmo		Apollo: 	23.22 fps 	APFast: 	51.82 fps 	Chronos: 	13.14 fps 	CHFast: 	19.60 fps 	
16X Slowmo		Aion: 	22.59 fps 	

Topaz Video AI  v6.0.1
System Information
OS: Windows v11.24
CPU: AMD Ryzen 9 5900X 12-Core Processor              31.927 GB
GPU: NVIDIA GeForce RTX 4080 SUPER  15.671 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	27.10 fps 	2X: 	10.99 fps 	4X: 	03.01 fps 	
Iris		1X: 	26.92 fps 	2X: 	14.88 fps 	4X: 	03.76 fps 	
Proteus		1X: 	28.92 fps 	2X: 	14.88 fps 	4X: 	03.93 fps 	
Gaia		1X: 	10.96 fps 	2X: 	07.42 fps 	4X: 	03.75 fps 	
Nyx		1X: 	12.58 fps 	2X: 	09.91 fps 	
Nyx Fast		1X: 	22.71 fps 	
Rhea		4X: 	03.48 fps 	
RXL		4X: 	03.43 fps 	
Hyperion HDR		1X: 	23.84 fps 	
4X Slowmo		Apollo: 	33.04 fps 	APFast: 	66.60 fps 	Chronos: 	23.37 fps 	CHFast: 	27.91 fps 	
16X Slowmo		Aion: 	39.35 fps 	

RTX 5090 anyone ? lol :grin:

1 Like

Everyone already on a PC wishes this was true, but it is far from it.

2 Likes
Topaz Video AI  v6.0.2
System Information
OS: Windows v10.22
CPU: AMD Ryzen Threadripper 3970X 32-Core Processor   127.87 GB
GPU: NVIDIA GeForce RTX 3090  23.756 GB
Processing Settings
device: -2 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	24.52 fps 	2X: 	12.20 fps 	4X: 	03.69 fps 	
Iris		1X: 	22.28 fps 	2X: 	13.87 fps 	4X: 	03.68 fps 	
Proteus		1X: 	22.93 fps 	2X: 	14.35 fps 	4X: 	03.84 fps 	
Gaia		1X: 	08.31 fps 	2X: 	05.74 fps 	4X: 	03.23 fps 	
Nyx		1X: 	10.26 fps 	2X: 	08.37 fps 	
Nyx Fast		1X: 	20.49 fps 	
Rhea		4X: 	03.07 fps 	
RXL		4X: 	02.91 fps 	
Hyperion HDR		1X: 	21.74 fps 	
4X Slowmo		Apollo: 	33.29 fps 	APFast: 	60.48 fps 	Chronos: 	19.00 fps 	CHFast: 	27.21 fps 	
16X Slowmo		Aion: 	24.75 fps 	

No thanks:
compute-video-ai

Topaz Video AI  v6.0.3
System Information
OS: Windows v11.24
CPU: Intel(R) Xeon(R) w5-2465X  127.25 GB
GPU: NVIDIA GeForce RTX 4070  11.73 GB
GPU: NVIDIA RTX A4000  15.79 GB
Processing Settings
device: 0 vram: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	18.20 fps 	2X: 	12.86 fps 	4X: 	03.57 fps 	
Iris		1X: 	18.52 fps 	2X: 	11.18 fps 	4X: 	03.23 fps 	
Proteus		1X: 	17.72 fps 	2X: 	12.14 fps 	4X: 	04.21 fps 	
Gaia		1X: 	06.13 fps 	2X: 	04.22 fps 	4X: 	02.90 fps 	
Nyx		1X: 	07.19 fps 	2X: 	06.13 fps 	
Nyx Fast		1X: 	13.36 fps 	
Rhea		4X: 	02.34 fps 	
RXL		4X: 	02.11 fps 	
Hyperion HDR		1X: 	17.90 fps 	
4X Slowmo		Apollo: 	24.16 fps 	APFast: 	54.53 fps 	Chronos: 	13.06 fps 	CHFast: 	20.42 fps 	
16X Slowmo		Aion: 	ERR fps 	

Topaz Video AI  v6.0.3
System Information
OS: Windows v11.23
CPU: AMD Ryzen 9 5950X 16-Core Processor              31.926 GB
GPU: NVIDIA GeForce RTX 4070 Ti SUPER  15.687 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		    1X: 	25.86 fps 	2X: 	11.13 fps 	4X: 	02.88 fps 	
Iris		    1X: 	24.76 fps 	2X: 	14.36 fps 	4X: 	03.88 fps 	
Proteus		    1X: 	25.64 fps 	2X: 	13.68 fps 	4X: 	04.00 fps 	
Gaia		    1X: 	09.07 fps 	2X: 	06.22 fps 	4X: 	03.65 fps 	
Nyx		        1X: 	10.61 fps 	2X: 	08.86 fps 	
Nyx Fast	    1X: 	19.60 fps 	
Rhea		    4X: 	03.32 fps 	
RXL		        4X: 	02.99 fps 	
Hyperion HDR    1X: 	24.33 fps 	
4X Slowmo		Apollo: 	32.51 fps 	APFast: 	66.73 fps 	Chronos: 	19.81 fps 	CHFast: 	28.89 fps 	
16X Slowmo		Aion: 	39.28 fps 	

Can you link sauce please?

Oops. Thought I had.

Looks like a performance regression here. I guess that’s because Topaz Video AI has no support for Blackwell yet.

Update: NVIDIA confirmed to us that apps using Tensor RT need an update to see optimal performance on Blackwell.

Below the picture. It all comes in good time.