As of right now, the 3080 will give you more than double the speed.
I might be assuming things in what I’m about to say, so keep that in mind.
The reason the 3080 gets double the speed is because TVAI implemented the ability to use it’s RT cores. So, even if they make the same improvements for AMD cards, they will still be much slower than the Nvidia cards—If RTX feature performance in games is any sort of inductor.
My main machine benchmark.
And here’s my new server computer:
Topaz Video AI v3.1.10
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 9 7900X 12-Core Processor 31.159 GB
GPU: AMD Radeon RX 6900 XT 15.954 GB
GPU: AMD Radeon(TM) Graphics 0.47445 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 7.87 fps 2X: 4.01 fps 4X: 1.53 fps
Proteus 1X: 5.72 fps 2X: 3.63 fps 4X: 1.51 fps
Gaia 1X: 5.04 fps 2X: 3.33 fps 4X: 2.24 fps
4X Slowmo Apollo: 13.17 fps Chronos: 7.01 fps Chronos Fast: 8.79 fps
