Video AI v3.3.X - User Benchmarking Results

Topaz Video AI  v3.3.1
System Information
OS: Windows v11.22
CPU: AMD Ryzen 9 5950X 16-Core Processor              63.902 GB
GPU: NVIDIA GeForce RTX 3070  7.8428 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	15.30 fps 	2X: 	09.31 fps 	4X: 	02.54 fps 	
Proteus		1X: 	15.02 fps 	2X: 	09.10 fps 	4X: 	02.48 fps 	
Gaia		1X: 	04.97 fps 	2X: 	03.41 fps 	4X: 	02.29 fps 	
4X Slowmo		Apollo: 	18.62 fps 	APFast: 	54.35 fps 	Chronos: 	11.32 fps 	CHFast: 	18.67 fps 


Topaz Video AI  v3.3.3
System Information
OS: Windows v11.22
CPU: AMD Ryzen 9 5950X 16-Core Processor              63.902 GB
GPU: NVIDIA GeForce RTX 3070  7.8428 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	15.18 fps 	2X: 	09.44 fps 	4X: 	02.76 fps 	
Proteus		1X: 	15.03 fps 	2X: 	09.37 fps 	4X: 	02.72 fps 	
Gaia		1X: 	04.96 fps 	2X: 	03.41 fps 	4X: 	02.29 fps 	
4X Slowmo		Apollo: 	18.58 fps 	APFast: 	46.47 fps 	Chronos: 	11.30 fps 	CHFast: 	18.56 fps 	


Topaz Video AI  v3.3.5
System Information
OS: Windows v11.22
CPU: AMD Ryzen 9 5950X 16-Core Processor              63.907 GB
GPU: NVIDIA GeForce RTX 3070  7.8428 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	15.13 fps 	2X: 	09.07 fps 	4X: 	02.43 fps 	
Proteus		1X: 	14.97 fps 	2X: 	08.99 fps 	4X: 	02.41 fps 	
Gaia		1X: 	04.96 fps 	2X: 	03.38 fps 	4X: 	02.22 fps 	
4X Slowmo		Apollo: 	17.99 fps 	APFast: 	45.07 fps 	Chronos: 	11.24 fps 	CHFast: 	18.51 fps

Just tried the same 1080p to 4k project on an HP Z420 and it’s estimating 32 days.

Any suggestions as to a better PC to make this a lot faster would be most welcome :slight_smile:

I though that’s where I posted this?

Ok, two questions:
How long is your 1080p input file?
What model are you going to use?

Then I could give you a rough estimation of the duration on a M1 Pro 10c/16c and on a M2 Ultra 24c/60c.

All in all you’ll apparently get the fastest speeds with a RTX 4090 but still need a decent CPU as it seems - so maybe your old PC won’t cut it.
But still, a new PC with fast CPU and GTX 4090 will be somewhat cheaper than a Mac Studio M2 ultra. The M2 ultra will consume quite less power of course.

Topaz Video AI  v3.3.3
System Information
OS: Windows v10.22
CPU: 13th Gen Intel(R) Core(TM) i7-13700K  127.75 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	31.97 fps 	2X: 	14.93 fps 	4X: 	03.61 fps 	
Proteus		1X: 	24.61 fps 	2X: 	12.56 fps 	4X: 	03.67 fps 	
Gaia		1X: 	14.20 fps 	2X: 	09.14 fps 	4X: 	03.62 fps 	
4X Slowmo		Apollo: 	36.44 fps 	APFast: 	71.55 fps 	Chronos: 	30.74 fps 	CHFast: 	31.29 fps 	

1 Like
Topaz Video AI  v3.3.6
System Information
OS: Windows v11.22
CPU: 13th Gen Intel(R) Core(TM) i9-13900K  127.75 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	40.04 fps 	2X: 	17.74 fps 	4X: 	04.46 fps 	
Proteus		1X: 	32.96 fps 	2X: 	15.64 fps 	4X: 	04.37 fps 	
Gaia		1X: 	15.90 fps 	2X: 	11.03 fps 	4X: 	04.52 fps 	
4X Slowmo		Apollo: 	41.76 fps 	APFast: 	72.86 fps 	Chronos: 	33.38 fps 	CHFast: 	34.06 fps 	

Topaz Video AI  v3.3.6
System Information
OS: Windows v11.22
CPU: 13th Gen Intel(R) Core(TM) i9-13900K  127.75 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis		1X: 	192.54 fps 	2X: 	83.06 fps 	4X: 	25.03 fps 	
Proteus		1X: 	155.17 fps 	2X: 	68.01 fps 	4X: 	23.00 fps 	
Gaia		1X: 	83.24 fps 	2X: 	59.12 fps 	4X: 	31.16 fps 	
4X Slowmo		Apollo: 	219.02 fps 	APFast: 	464.94 fps 	Chronos: 	159.18 fps 	CHFast: 	216.71 fps 	

Topaz Video AI  v3.3.6
System Information
OS: Windows v10.22
CPU: 13th Gen Intel(R) Core(TM) i7-13700K  127.75 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	30.61 fps 	2X: 	13.78 fps 	4X: 	03.71 fps 	
Proteus		1X: 	26.42 fps 	2X: 	10.16 fps 	4X: 	03.47 fps 	
Gaia		1X: 	14.38 fps 	2X: 	09.84 fps 	4X: 	03.71 fps 	
4X Slowmo		Apollo: 	34.69 fps 	APFast: 	62.79 fps 	Chronos: 	29.23 fps 	CHFast: 	29.51 fps 	

Got my RTX 4070 today, atm installed on my proxmox host with pci passthrough int a win 11 VM which has 8 cores and 16GB ram. this config is at least 4 time faster than my mb pro m1 max with 16 GB ram.

Topaz Video AI Beta  v3.3.6.2.b
System Information
OS: Windows v11.22
CPU: AMD EPYC 7282 16-Core Processor                  15.971 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
Processing Settings
device: -2 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	16.71 fps 	2X: 	07.08 fps 	4X: 	01.78 fps 	
Proteus		1X: 	15.31 fps 	2X: 	07.10 fps 	4X: 	01.93 fps 	
Gaia		1X: 	06.09 fps 	2X: 	04.18 fps 	4X: 	01.86 fps 	
4X Slowmo		Apollo: 	23.91 fps 	APFast: 	44.38 fps 	Chronos: 	12.12 fps 	CHFast: 	17.81 fps 	

Topaz Video AI  v3.3.7
System Information
OS: Windows v11.22
CPU: AMD EPYC 7282 16-Core Processor                  15.971 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
GPU: NVIDIA GeForce RTX 4070  11.744 GB
Processing Settings
device: -2 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	17.15 fps 	2X: 	07.03 fps 	4X: 	01.99 fps 	
Proteus		1X: 	15.33 fps 	2X: 	06.75 fps 	4X: 	01.93 fps 	
Gaia		1X: 	06.07 fps 	2X: 	04.17 fps 	4X: 	01.94 fps 	
4X Slowmo		Apollo: 	23.57 fps 	APFast: 	34.12 fps 	Chronos: 	12.73 fps 	CHFast: 	18.34 fps 	

1 Like

Is your System Ram DDR4? I also have RXT4070CPU 13900k, I changed from DDR4(3200MHz) to DDR5(6100MHz) and the speed is very fast (e.g. Artemis 2X and Proteus 2X values from 9fps to 12fps)

Please add Iris to the benchmarks. It’s probably the most popular model currently.

1 Like
Topaz Video AI  v3.3.8
System Information
OS: Windows v10.22
CPU: AMD Ryzen 7 3700X 8-Core Processor               63.952 GB
GPU: NVIDIA GeForce RTX 4090  23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	25.88 fps 	2X: 	08.03 fps 	4X: 	02.08 fps 	
Proteus		1X: 	15.81 fps 	2X: 	07.26 fps 	4X: 	01.94 fps 	
Gaia		1X: 	15.33 fps 	2X: 	07.80 fps 	4X: 	02.08 fps 	
4X Slowmo		Apollo: 	27.65 fps 	APFast: 	32.27 fps 	Chronos: 	23.70 fps 	CHFast: 	22.24 fps 	

NVIDIA STUDIO DRIVER INSTALL ver 536.67

Topaz Video AI  v3.3.8
System Information
OS: Windows v10.22
CPU: AMD Ryzen Threadripper 3970X 32-Core Processor   127.87 GB
GPU: NVIDIA GeForce RTX 3090  23.77 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	24.07 fps 	2X: 	09.96 fps 	4X: 	02.82 fps 	
Proteus		1X: 	24.07 fps 	2X: 	09.72 fps 	4X: 	02.74 fps 	
Gaia		1X: 	08.54 fps 	2X: 	05.73 fps 	4X: 	02.81 fps 	
4X Slowmo		Apollo: 	29.95 fps 	APFast: 	50.89 fps 	Chronos: 	18.77 fps 	CHFast: 	25.72 fps 	

This is a MacBook Pro, not a desktop:

Topaz Video AI  v3.3.5
System Information
OS: Mac v14
CPU: Apple M2 Max  32 GB
GPU: Apple M2 Max  21.333 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	09.81 fps 	2X: 	06.42 fps 	4X: 	02.10 fps 	
Proteus		1X: 	10.04 fps 	2X: 	06.43 fps 	4X: 	02.07 fps 	
Gaia		1X: 	03.30 fps 	2X: 	02.44 fps 	4X: 	01.71 fps 	
4X Slowmo		Apollo: 	07.69 fps 	APFast: 	28.82 fps 	Chronos: 	03.15 fps 	CHFast: 	05.33 fps 	

Your CPU generally outperforms my 7950x due to a better memory controller :cry:

I bought into the AM5 platform because the 13900K socket is at the end of the line so I will have at least one more generation of CPU upgrades
hopefully 2

2 Likes
Topaz Video AI  v3.3.5
System Information
OS: Windows v11.22
CPU: AMD Ryzen 9 5900X 12-Core Processor              31.912 GB
GPU: NVIDIA GeForce RTX 3070  7.8428 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	14.20 fps 	2X: 	07.24 fps 	4X: 	01.99 fps 	
Proteus		1X: 	13.11 fps 	2X: 	06.98 fps 	4X: 	01.92 fps 	
Gaia		1X: 	04.84 fps 	2X: 	03.32 fps 	4X: 	01.97 fps 	
4X Slowmo		Apollo: 	18.00 fps 	APFast: 	38.80 fps 	Chronos: 	10.90 fps 	CHFast: 	17.36 fps 	

Personal computer (Intel + Nvidia):

Topaz Video AI  v3.3.9
System Information
OS: Windows v11.22
CPU: 13th Gen Intel(R) Core(TM) i9-13900K  63.576 GB
GPU: NVIDIA GeForce RTX 4080  15.688 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	29.75 fps 	2X: 	15.92 fps 	4X: 	04.36 fps 	
Proteus		1X: 	26.41 fps 	2X: 	14.71 fps 	4X: 	04.18 fps 	
Gaia		1X: 	10.67 fps 	2X: 	07.28 fps 	4X: 	04.60 fps 	
4X Slowmo		Apollo: 	36.16 fps 	APFast: 	73.63 fps 	Chronos: 	23.63 fps 	CHFast: 	29.93 fps 	

Work computer (AMD + AMD):

Topaz Video AI  v3.3.9
System Information
OS: Windows v11.22
CPU: AMD Ryzen 9 7950X3D 16-Core Processor            127.15 GB
GPU: AMD Radeon PRO W7900  44.942 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	16.07 fps 	2X: 	09.26 fps 	4X: 	02.55 fps 	
Proteus		1X: 	15.21 fps 	2X: 	08.60 fps 	4X: 	02.58 fps 	
Gaia		1X: 	07.25 fps 	2X: 	04.73 fps 	4X: 	02.83 fps 	
4X Slowmo		Apollo: 	18.22 fps 	APFast: 	54.99 fps 	Chronos: 	10.76 fps 	CHFast: 	16.14 fps 	

No secret that TVAI is highly optimized for Nvidia, but kind of striking to see the disparity.

One thing to note: the all AMD machine, while not as fast, handles work much more elegantly. Barely even breaks a sweat, whereas the Intel + Nvidia machine sounds like a jet trying to takeoff


Similar to Apple silicon. Not really as fast as Nvidia, but MUCH less power consumption leading to much less noise.

Seems to be a micro performance gain when you reduce the Vram from 1.0 to .8. Lower numbers tend to reverse the gain.

Mac Mini M1 - 512GB SSD - OS is Ventura 13.5 (not 13.05 as listed)

Topaz Video AI  v3.3.8
System Information
OS: Mac v13.05
CPU: Apple M1  16 GB
GPU: Apple M1  10.667 GB
Processing Settings
device: 0 vram: 0.8 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 	03.71 fps 	2X: 	02.48 fps 	4X: 	01.02 fps 	
Proteus		1X: 	03.73 fps 	2X: 	02.48 fps 	4X: 	00.98 fps 	
Gaia		1X: 	01.22 fps 	2X: 	00.90 fps 	4X: 	00.71 fps 	
4X Slowmo		Apollo: 	03.87 fps 	APFast: 	14.53 fps 	Chronos: 	01.31 fps 	CHFast: 	01.98 fps