Starting with Topaz Video AI v3.1.9 you will be able to run the models against standard inputs to able 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 results here.
Topaz Video AI v3.1.9
System Information
OS: Mac v13.0201
CPU: Apple M1 Max 64 GB
GPU: Apple M1 Max 48 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 8.18 fps 2X: 5.95 fps 4X: 2 fps
Proteus 1X: 8.89 fps 2X: 5.13 fps 4X: 1.92 fps
Gaia 1X: 2.7 fps 2X: 1.87 fps 4X: 1.48 fps
4X Slowmo Apollo: 8.41 fps Chronos: 2.72 fps Chronos Fast: 2.34 fps
We will be creating a new thread for each “major” release of Video AI. Be sure to include the full version you are running when posting benchmarking results as replies to threads, this will be useful as we continue to release updates to Video AI.
Suggest the Video AI version be included in the results so there is no doubt as to what version is being used.
Edit: The text output does include the version # already. The benchmark GUI doesn’t however so it would be good to have it added there as people like posting screenshots of it.
The Amd Epyc Cpu is only used with 4 cores and 8 MT, it’s a VM / virtual machine on a cloud computer.
the CPu is shared with other people in the data center.
The Amd Epyc Cpu is only used with 4 cores and 8 MT, it’s a VM / virtual machine on a cloud computer.
the CPu is shared with other people in the data center.
Thats not real the difference in performance between nvidia 3rd and 4th series to be so small especially in Proteus … Very bad Topaz software optimization i guess …
Well I did it again, because the one I posted before, I had other applications open, maybe that’s why it wasn’t high. This second one is already much better, but it’s not that high yet, however I have a good RTX 3090, I saw the other one with its 3080 it was high, why am I not so high? Is it because of my AMD? I don’t understand, because the encoding is fast when I export my videos with TVEAI
I just tried in 1280x720 it’s very high, look below: (why in 1920x1080 it’s less? I don’t understand)
ngl: compared to the M1 Max at the top of this post I expected higher numbers, though that’s obvs a beefier rig than my MacBook. I hope there’s more tuning to come for the M2 chips.
Topaz Video AI v3.1.9
System Information
OS: Mac v13.0201
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: 10.05 fps 2X: 6.62 fps 4X: 1.83 fps
Proteus 1X: 10.37 fps 2X: 5.82 fps 4X: 1.81 fps
Gaia 1X: 3.26 fps 2X: 2.07 fps 4X: 1.46 fps
4X Slowmo Apollo: 8.99 fps Chronos: 2.81 fps Chronos Fast: 5.07 fps
this is normal that if you do a processing by x2 or x4 that your speed to process it is slower. it make the picture bigger by x2 or x4, it use much more power from your card. if you compare your result with others you’ll notice that it’s the same for everybody. but your result are a bit slow for a 720p processing in x1. i have a A4500 RTX on hand which is slower than a 3090, so maybe there is something wrong on your system, like maybe something which use the Gpu at the same time. i suggest you to check well your system, drivers, etc…
