Users can run benchmarking (Process > Benchmark, or, Ctrl/Cmd + B) to compare results across different machines.
Topaz Video AI v6.1.0
System Information
OS: Mac v14.03
CPU: Apple M3 Max 128 GB
GPU: Apple M3 Max 96 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 11.53 fps 2X: 07.24 fps 4X: 02.64 fps
Iris 1X: 08.31 fps 2X: 04.77 fps 4X: 01.55 fps
Proteus 1X: 09.30 fps 2X: 07.19 fps 4X: 02.13 fps
Gaia 1X: 03.20 fps 2X: 02.32 fps 4X: 01.79 fps
Nyx 1X: 03.75 fps 2X: 04.51 fps
Nyx Fast 1X: 12.59 fps
Rhea 4X: 00.99 fps
RXL 4X: 01.06 fps
Hyperion HDR 1X: 62.47 fps
4X Slowmo Apollo: 13.17 fps APFast: 47.00 fps Chronos: 04.51 fps CHFast: 07.08 fps
16X Slowmo Aion: 13.34 fps
Topaz Video AI v6.1.0
System Information
OS: Mac v14.03
CPU: Apple M3 Max 128 GB
GPU: Apple M3 Max 96 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 3840x2160
Benchmark Results
Artemis 1X: 02.64 fps 2X: 01.59 fps 4X: 00.53 fps
Iris 1X: 02.12 fps 2X: 01.16 fps 4X: 00.33 fps
Proteus 1X: 02.08 fps 2X: 01.47 fps 4X: 00.47 fps
Gaia 1X: 00.66 fps 2X: 00.47 fps 4X: 00.36 fps
Nyx 1X: 00.87 fps 2X: 00.82 fps
Nyx Fast 1X: 01.94 fps
Rhea 4X: 00.19 fps
RXL 4X: 00.20 fps
Hyperion HDR 1X: 19.33 fps
4X Slowmo Apollo: 02.46 fps APFast: 10.35 fps Chronos: 01.01 fps CHFast: 01.53 fps
16X Slowmo Aion: ... fps
Topaz Video AI v6.1.0
System Information
OS: Mac v15.0301
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: 15.97 fps 2X: 08.60 fps 4X: 03.06 fps
Iris 1X: 09.69 fps 2X: 04.60 fps 4X: 02.36 fps
Proteus 1X: 16.20 fps 2X: 09.63 fps 4X: 03.09 fps
Gaia 1X: 06.24 fps 2X: 04.15 fps 4X: 02.70 fps
Nyx 1X: 03.97 fps 2X: 05.08 fps
Nyx Fast 1X: 14.21 fps
Rhea 4X: 01.37 fps
RXL 4X: 01.37 fps
Hyperion HDR 1X: 51.65 fps
4X Slowmo Apollo: 19.81 fps APFast: 63.43 fps Chronos: 05.99 fps CHFast: 07.60 fps
16X Slowmo Aion: 17.40 fps
1 Like
Topaz Video AI v6.1.0
System Information
OS: Mac v15.0301
CPU: Apple M2 Ultra 64 GB
GPU: Apple M2 Ultra 48 GB
Processing Settings
device: 0 vram: 0.1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis 1X: 68.15 fps 2X: 38.79 fps 4X: 13.73 fps
Iris 1X: 53.12 fps 2X: 20.19 fps 4X: 10.86 fps
Proteus 1X: 63.02 fps 2X: 46.99 fps 4X: 16.02 fps
Gaia 1X: 30.50 fps 2X: 17.90 fps 4X: 11.85 fps
Nyx 1X: 16.09 fps 2X: 15.14 fps
Nyx Fast 1X: 56.87 fps
Rhea 4X: 05.75 fps
RXL 4X: 06.27 fps
Hyperion HDR 1X: 124.23 fps
4X Slowmo Apollo: 66.64 fps APFast: 209.24 fps Chronos: 21.85 fps CHFast: 30.23 fps
16X Slowmo Aion: 83.17 fps
Topaz Video AI v6.1.0
System Information
OS: Windows v10.22
CPU: Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz 63.936 GB
GPU: NVIDIA GeForce RTX 3060 11.826 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 08.86 fps 2X: 05.76 fps 4X: 01.54 fps
Iris 1X: 08.56 fps 2X: 05.64 fps 4X: 01.61 fps
Proteus 1X: 08.87 fps 2X: 06.51 fps 4X: 02.19 fps
Gaia 1X: 03.10 fps 2X: 02.16 fps 4X: 01.39 fps
Nyx 1X: 03.86 fps 2X: 03.27 fps
Nyx Fast 1X: 07.57 fps
Rhea 4X: 01.18 fps
RXL 4X: 01.12 fps
Hyperion HDR 1X: 11.94 fps
4X Slowmo Apollo: 13.75 fps APFast: 37.59 fps Chronos: 07.59 fps CHFast: 12.70 fps
16X Slowmo Aion: 22.88 fps
Topaz Video AI v6.1.0
System Information
OS: Windows v11.24
CPU: Intel(R) Core(TM) i9-14900KF 63.725 GB
GPU: NVIDIA GeForce RTX 4090 23.576 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 37.49 fps 2X: 17.40 fps 4X: 04.69 fps
Iris 1X: 37.54 fps 2X: 21.42 fps 4X: 05.46 fps
Proteus 1X: 41.45 fps 2X: 20.63 fps 4X: 05.79 fps
Gaia 1X: 15.52 fps 2X: 10.77 fps 4X: 05.33 fps
Nyx 1X: 17.25 fps 2X: 14.35 fps
Nyx Fast 1X: 30.76 fps
Rhea 4X: 05.31 fps
RXL 4X: 04.78 fps
Hyperion HDR 1X: 27.22 fps
4X Slowmo Apollo: 42.02 fps APFast: 75.30 fps Chronos: 32.57 fps CHFast: 36.62 fps
16X Slowmo Aion: 34.98 fps
Topaz Video AI v6.1.0
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: 0.9 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 00.43 fps 2X: 00.85 fps 4X: 00.38 fps
Iris 1X: 01.23 fps 2X: 00.81 fps 4X: 00.17 fps
Proteus 1X: 01.69 fps 2X: 01.18 fps 4X: 00.33 fps
Gaia 1X: 00.51 fps 2X: 00.34 fps 4X: 00.21 fps
Nyx 1X: 00.58 fps 2X: 00.60 fps
Nyx Fast 1X: 01.52 fps
Rhea 4X: 00.20 fps
RXL 4X: 00.22 fps
Hyperion HDR 1X: 21.80 fps
4X Slowmo Apollo: 01.44 fps APFast: 06.39 fps Chronos: 00.30 fps CHFast: 00.67 fps
16X Slowmo Aion: 01.35 fps
Topaz Video AI v6.1.0
System Information
OS: Windows v11.23
CPU: AMD Ryzen 9 5900X 12-Core Processor 31.922 GB
GPU: NVIDIA GeForce RTX 3080 Ti 11.816 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 22.51 fps 2X: 10.09 fps 4X: 02.83 fps
Iris 1X: 21.41 fps 2X: 12.60 fps 4X: 03.83 fps
Proteus 1X: 22.21 fps 2X: 13.89 fps 4X: 03.84 fps
Gaia 1X: 08.02 fps 2X: 05.52 fps 4X: 03.51 fps
Nyx 1X: 09.74 fps 2X: 07.97 fps
Nyx Fast 1X: 18.81 fps
Rhea 4X: 03.13 fps
RXL 4X: 02.93 fps
Hyperion HDR 1X: 25.33 fps
4X Slowmo
Apollo: 32.13 fps
APFast: 54.80 fps
Chronos: 18.03 fps
CHFast: 28.31 fps
16X Slowmo
Aion: 39.04 fps
Topaz Video AI v6.1.0
System Information
OS: Windows v11.24
CPU: AMD Ryzen 9 7900X 12-Core Processor 31.103 GB
GPU: NVIDIA GeForce RTX 4070 Ti 11.715 GB
GPU: AMD Radeon(TM) Graphics 0.47445 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 24.24 fps 2X: 12.94 fps 4X: 03.66 fps
Iris 1X: 24.88 fps 2X: 14.95 fps 4X: 03.92 fps
Proteus 1X: 23.45 fps 2X: 15.85 fps 4X: 04.66 fps
Gaia 1X: 08.25 fps 2X: 05.70 fps 4X: 03.70 fps
Nyx 1X: 09.44 fps 2X: 08.29 fps
Nyx Fast 1X: 16.71 fps
Rhea 4X: 03.17 fps
RXL 4X: 02.73 fps
Hyperion HDR 1X: 23.20 fps
4X Slowmo
Apollo: 32.95 fps
APFast: 65.90 fps
Chronos: 18.55 fps
CHFast: 27.24 fps
16X Slowmo
Aion: ERR fps
Odd. I’ve never had a problem with Aion on this computer before.
27 inch iMac 2017
Topaz Video AI v6.1.0
System Information
OS: Mac v13.0704
CPU: Intel(R) Core(TM) i5-7600 CPU @ 3.50GHz 16 GB
GPU: AMD Radeon Pro 575 4 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 01.38 fps 2X: 00.91 fps 4X: 00.37 fps
Iris 1X: 01.00 fps 2X: 00.59 fps 4X: 00.19 fps
Proteus 1X: 01.21 fps 2X: 00.79 fps 4X: 00.33 fps
Gaia 1X: 00.42 fps 2X: 00.29 fps 4X: 00.23 fps
Nyx 1X: 00.60 fps 2X: 00.56 fps
Nyx Fast 1X: 01.44 fps
Rhea 4X: 00.19 fps
RXL 4X: 00.21 fps
Hyperion HDR 1X: 08.44 fps
4X Slowmo Apollo: 01.24 fps APFast: 04.44 fps Chronos: 00.27 fps CHFast: 00.59 fps
16X Slowmo Aion: 01.03 fps
27 inch iMac 2017
Topaz Video AI v6.1.0
System Information
OS: Mac v13.0704
CPU: Intel(R) Core(TM) i5-7600 CPU @ 3.50GHz 16 GB
GPU: AMD Radeon Pro 575 4 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 720x480
Benchmark Results
Artemis 1X: 08.26 fps 2X: 05.46 fps 4X: 02.37 fps
Iris 1X: 07.24 fps 2X: 04.11 fps 4X: 01.30 fps
Proteus 1X: 07.63 fps 2X: 05.22 fps 4X: 01.98 fps
Gaia 1X: 02.87 fps 2X: 02.03 fps 4X: 01.59 fps
Nyx 1X: 02.47 fps 2X: 02.38 fps
Nyx Fast 1X: 06.15 fps
Rhea 4X: 01.29 fps
RXL 4X: 01.43 fps
Hyperion HDR 1X: 31.82 fps
4X Slowmo Apollo: 07.05 fps APFast: 26.46 fps Chronos: 02.06 fps CHFast: 03.83 fps
16X Slowmo Aion: 07.22 fps
27 inch iMac 2017
Topaz Video AI v6.1.0
System Information
OS: Mac v13.0704
CPU: Intel(R) Core(TM) i5-7600 CPU @ 3.50GHz 16 GB
GPU: AMD Radeon Pro 575 4 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 480x360
Benchmark Results
Artemis 1X: 13.17 fps 2X: 08.42 fps 4X: 03.19 fps
Iris 1X: 11.47 fps 2X: 05.46 fps 4X: 02.26 fps
Proteus 1X: 12.74 fps 2X: 07.05 fps 4X: 03.29 fps
Gaia 1X: 05.40 fps 2X: 03.83 fps 4X: 02.82 fps
Nyx 1X: 07.32 fps 2X: 06.28 fps
Nyx Fast 1X: 17.05 fps
Rhea 4X: 02.22 fps
RXL 4X: 02.46 fps
Hyperion HDR 1X: 38.67 fps
4X Slowmo Apollo: 12.65 fps APFast: 37.42 fps Chronos: 03.00 fps CHFast: 05.29 fps
16X Slowmo Aion: 11.67 fps
Hey jo.vo,
To what would you attribute these stellar benchmark results? There appears to be other M2 Ultra processor benchmarks, and even some M3 benchmarks with even more RAM. I realize your results are for 720x480 but just looking at the Artemis 1X 68.15 fps result, that is 2.5x greater than the next fastest Artemis 1X fps (27.03) and way above the average I’ve unscientifically calculated average of 12.65 fps using all different Video AI version benchmark results (5.0.0 to 6.1.X).
Your VRAM setting is unusually low at 10%, do you think this is the solution or is it that you are running on a Mac Studio, or something else all together?
Thanks,
Kent
1 Like
So you found the key yourselves.
Yes, setting RAM to 10% actually leads to faster performance on AppleSilicon (and here on both the Studio with M2ultra as well as the MacBook Pro with M1 Pro that I have here) - but only for low resolutions.
With higher resolutions there can be mixed results with RAM at 85% being faster for some models or for 2x while the others are faster at 100%. 4x encodes are about always faster with RAM at 100%.
Oh, and yes: a M2 Ultra is still faster than m3 or even m4 non-ultra.
1 Like
Topaz Video AI v6.1.0
System Information
OS: Windows v11.23
CPU: AMD Ryzen 9 7900 12-Core Processor 63.143 GB
GPU: NVIDIA GeForce RTX 4080 SUPER 15.671 GB
GPU: AMD Radeon(TM) Graphics 0.47446 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 22.13 fps 2X: 12.65 fps 4X: 03.94 fps
Iris 1X: 24.50 fps 2X: 17.89 fps 4X: 03.31 fps
Proteus 1X: 21.59 fps 2X: 12.26 fps 4X: 03.96 fps
Gaia 1X: 09.19 fps 2X: 06.25 fps 4X: 03.68 fps
Nyx 1X: 10.96 fps 2X: 08.99 fps
Nyx Fast 1X: 18.00 fps
Rhea 4X: 03.78 fps
RXL 4X: 03.17 fps
Hyperion HDR 1X: 27.00 fps
4X Slowmo Apollo: 33.82 fps APFast: 74.19 fps Chronos: 20.23 fps CHFast: 29.16 fps
16X Slowmo Aion: 46.87 fps
Topaz Video AI v6.1.0
System Information
OS: Windows v11.23
CPU: AMD Ryzen 9 7900 12-Core Processor 63.143 GB
GPU: NVIDIA GeForce RTX 4080 SUPER 15.671 GB
GPU: AMD Radeon(TM) Graphics 0.47446 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 3840x2160
Benchmark Results
Artemis 1X: 04.72 fps 2X: 02.70 fps 4X: 00.86 fps
Iris 1X: 05.23 fps 2X: 03.80 fps 4X: 00.71 fps
Proteus 1X: 04.63 fps 2X: 02.67 fps 4X: 00.85 fps
Gaia 1X: 01.97 fps 2X: 01.33 fps 4X: 00.80 fps
Nyx 1X: 01.89 fps 2X: 02.05 fps
Nyx Fast 1X: 02.99 fps
Rhea 4X: 00.81 fps
RXL 4X: 00.70 fps
Hyperion HDR 1X: 08.85 fps
4X Slowmo Apollo: 12.73 fps APFast: 22.42 fps Chronos: 04.34 fps CHFast: 07.66 fps
16X Slowmo Aion: 11.21 fps
For your AION ERR FPS result, try rerunning the benchmark. I’ve had that happen before as well after an update.
After restarting the software and rerunning the benchmark, it was able to successfully complete. Not sure what causes it, but that was the workaround for me.
1 Like
Sure enough.
Topaz Video AI v6.1.0
System Information
OS: Windows v11.24
CPU: AMD Ryzen 9 7900X 12-Core Processor 31.103 GB
GPU: NVIDIA GeForce RTX 4070 Ti 11.715 GB
GPU: AMD Radeon(TM) Graphics 0.47445 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 26.89 fps 2X: 12.62 fps 4X: 03.60 fps
Iris 1X: 25.36 fps 2X: 15.47 fps 4X: 03.95 fps
Proteus 1X: 23.65 fps 2X: 15.96 fps 4X: 04.81 fps
Gaia 1X: 08.27 fps 2X: 05.75 fps 4X: 03.73 fps
Nyx 1X: 09.51 fps 2X: 08.30 fps
Nyx Fast 1X: 16.86 fps
Rhea 4X: 03.21 fps
RXL 4X: 02.77 fps
Hyperion HDR 1X: 23.75 fps
4X Slowmo
Apollo: 33.58 fps
APFast: 71.27 fps
Chronos: 18.72 fps
CHFast: 27.80 fps
16X Slowmo
Aion: 31.32 fps
Before and after benchmark results from alpha release with optimizations for 50-series:
Note*
Some processing speeds are slower (Aion for example). These are likely due to change of CPU and non-optimized ram speed or tightened ram timings. The before results with the Ryzen 7 7800X3D had manually set ram timings and overclocked speed to 6200MT/s as well as high fclk.
The results from alpa with 50-series optimization are run with a Ryzen 9 9900X with only PBO activated and CO All -27 and regarding ram I’ve only enabled expo which run at 6000MT/s and much loser timing as well as default fclk.
Windows version also differ between the two as you can see. Benchmarks before optimization were run on Windows 11 23H2, benchmarks with optimizations on Windows 11 24H2.
Both benchmarks were done at fabric clock. Since 5080 is an overclocking beast, I’ll add a third benchmark with the alpha build where the rtx 5080 is overclocked, however, not overclocked to the brink of crashing - which is around +400-450. The overclocked benchmark was done at +350 core and +1500 memory with a tiny undervolt to reduce likelihood of a crash due to the transient load nature of VAi (Aion being the worst offender where power draw shifts between 20% and 80% several times per second), curve flattened at 1015mV
The 5080 doesn’t use more than at most, 80% power, even with no power limit set
Before optimization stock 5080 + tuned RAM and Ryzen 7 7800X3D:
Topaz Video AI Beta v6.0.4.0.b
System Information
OS: Windows v11.23
CPU: AMD Ryzen 7 7800X3D 8-Core Processor 31.604 GB
GPU: NVIDIA GeForce RTX 5080 15.517 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 25.02 fps 2X: 15.73 fps 4X: 04.83 fps
Iris 1X: 26.44 fps 2X: 15.08 fps 4X: 04.85 fps
Proteus 1X: 26.19 fps 2X: 19.37 fps 4X: 05.22 fps
Gaia 1X: 11.22 fps 2X: 07.73 fps 4X: 05.03 fps
Nyx 1X: 09.80 fps 2X: 08.03 fps
Nyx Fast 1X: 17.37 fps
Rhea 4X: 03.63 fps
RXL 4X: 03.48 fps
Hyperion HDR 1X: 33.59 fps
4X Slowmo Apollo: 32.49 fps AFast: 73.45 fps CH: 14.78 fps CHFast: 28.98 fps
16X Slowmo Aion: 52.62 fps
After optimization (alpha build) stock 5080 + Expo ram and Ryzen 9 9900X:
Topaz Video AI Alpha v6.1.1.1.a.trt
System Information
OS: Windows v11.24
CPU: AMD Ryzen 9 9900X 12-Core Processor 31.602 GB
GPU: NVIDIA GeForce RTX 5080 15.517 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 34.09 fps 2X: 16.45 fps 4X: 04.66 fps
Iris 1X: 33.13 fps 2X: 19.14 fps 4X: 05.30 fps
Proteus 1X: 34.37 fps 2X: 20.11 fps 4X: 05.47 fps
Gaia 1X: 10.69 fps 2X: 07.84 fps 4X: 04.95 fps
Nyx 1X: 10.00 fps 2X: 08.06 fps
Nyx Fast 1X: 23.06 fps
Rhea 4X: 04.20 fps
RXL 4X: 04.03 fps
Hyperion HDR 1X: 30.21 fps
4X Slowmo Apollo: 41.97 fps APFast: 69.74 fps Chronos: 27.07 fps CHFast: 38.19 fps
16X Slowmo Aion: 39.52 fps
After optimization (alpha build) overclocked and voltage limit 5080 + Expo ram and Ryzen 9 9900X:
Topaz Video AI Alpha v6.1.1.1.a.trt
System Information
OS: Windows v11.24
CPU: AMD Ryzen 9 9900X 12-Core Processor 31.602 GB
GPU: NVIDIA GeForce RTX 5080 15.517 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 36.38 fps 2X: 16.77 fps 4X: 04.66 fps
Iris 1X: 37.00 fps 2X: 20.10 fps 4X: 05.30 fps
Proteus 1X: 37.20 fps 2X: 19.80 fps 4X: 05.46 fps
Gaia 1X: 11.41 fps 2X: 08.35 fps 4X: 05.02 fps
Nyx 1X: 10.63 fps 2X: 08.43 fps
Nyx Fast 1X: 24.71 fps
Rhea 4X: 04.50 fps
RXL 4X: 04.28 fps
Hyperion HDR 1X: 32.31 fps
4X Slowmo Apollo: 43.47 fps APFast: 70.41 fps Chronos: 28.69 fps CHFast: 40.29 fps
16X Slowmo Aion: 46.94 fps
Looking at the generative models which seem to be the ones most affected by tensor cores, Artemis, Iris and Proteus specifically, the optimizations increase processing speed by about ~26-27%.
EDIT*
I went ahead and tuned my ram a bit and would like to show that ram speed and/or ram latency does have a significant impact on upscaling and some of the interpolation models. My 2x16GB 6000mhz@cl30 (with expo enabled) kit is now running at 6200mhz@cl30 with fclk at 2067, uclk=mclk and tighter sub-timings.
Apollo fast and 4x upscaling for the 4 basic models see a 10% uplift in processing speed. Some other around ~5%. So don’t neglect your ram.
VAi doesn’t use much ram, as it doesn’t store frames in ram. Ram is just used as a middle hand because frames are being processed by both CPU and GPU. Looking at upscaling as an example, and the ffmpeg export command. The GPU handles the generative part of enhancing a frame, while the CPU handles upscaling of frames, eg: scale=w=3840:h=2160:flags=lanczos:threads=0 with -sws_flags "spline+accurate_rnd+full_chroma_int" added before the filter graph which slightly refines the “scale” filter.
Reason some other models are seeing a ~1-2% difference is more likely just margin of error. Take Rhea and the basic models without upscaling as examples. There will always be a slight difference in processing speed even when running benchmarks back-to-back without changing any setting.
After optimization (alpha build) overclocked and voltage limit 5080 + manually tuned ram and Ryzen 9 9900X:
Topaz Video AI Alpha v6.1.1.1.a.trt
System Information
OS: Windows v11.24
CPU: AMD Ryzen 9 9900X 12-Core Processor 31.602 GB
GPU: NVIDIA GeForce RTX 5080 15.517 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 37.73 fps 2X: 19.17 fps 4X: 05.41 fps
Iris 1X: 37.22 fps 2X: 20.42 fps 4X: 06.06 fps
Proteus 1X: 37.30 fps 2X: 23.41 fps 4X: 06.33 fps
Gaia 1X: 11.53 fps 2X: 08.46 fps 4X: 05.79 fps
Nyx 1X: 10.63 fps 2X: 08.64 fps
Nyx Fast 1X: 25.06 fps
Rhea 4X: 04.23 fps
RXL 4X: 04.43 fps
Hyperion HDR 1X: 33.26 fps
4X Slowmo Apollo: 46.36 fps APFast: 77.09 fps Chronos: 28.91 fps CHFast: 41.14 fps
16X Slowmo Aion: 49.31 fps
2 Likes
Yes, RAM speed matters a lot for 2X and even more for 4X. Running the same 6200CL30 with optimized sub timings on my 7950X
Here are my results from this alpha for a 5090:
i got decent uplift in Artemis, Iris and Proteus 1X performance from 5090 over 4090. Although I see some 10% run to run differences in 1X results (not really in 2X/4X). Maybe something to improve in the benchmark.
2x and 4x seem to be limited by RAM/CPU speed.
Nyx fast, Chronos/Chronos Fast and Aion also see good uplift.
Most other models seem to be about the same.
Gains seem to be in-line with the general performance difference of 20-30% from 4090 to 5090.
Topaz Video AI Alpha v6.1.1.1.a.trt
System Information
OS: Windows v10.22
CPU: AMD Ryzen 9 7950X 16-Core Processor 31.71 GB
GPU: NVIDIA GeForce RTX 5090 31.349 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 50.65 fps 2X: 21.41 fps 4X: 05.78 fps
Iris 1X: 51.28 fps 2X: 21.92 fps 4X: 06.05 fps
Proteus 1X: 52.88 fps 2X: 22.94 fps 4X: 06.12 fps
Gaia 1X: 18.89 fps 2X: 13.77 fps 4X: 05.70 fps
Nyx 1X: 18.29 fps 2X: 12.39 fps
Nyx Fast 1X: 43.99 fps
Rhea 4X: 05.78 fps
RXL 4X: 05.76 fps
Hyperion HDR 1X: 45.23 fps
4X Slowmo Apollo: 48.47 fps APFast: 76.59 fps Chronos: 46.67 fps CHFast: 50.36 fps
16X Slowmo Aion: 43.08 fps
4090 on same system (with older TVAI 5.3 but that doesnt really matter from my experience):
Topaz Video AI Alpha v5.3.0.1.a.hyp.rxl
System Information
OS: Windows v10.22
CPU: AMD Ryzen 9 7950X 16-Core Processor 31.118 GB
GPU: NVIDIA GeForce RTX 4090 23.576 GB
GPU: AMD Radeon(TM) Graphics 0.47445 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 44.05 fps 2X: 18.96 fps 4X: 05.19 fps
Iris 1X: 42.82 fps 2X: 22.31 fps 4X: 05.99 fps
Proteus 1X: 41.98 fps 2X: 22.13 fps 4X: 06.17 fps
Gaia 1X: 15.66 fps 2X: 10.96 fps 4X: 05.60 fps
Nyx 1X: 17.64 fps 2X: 15.97 fps
Nyx Fast 1X: 31.61 fps
Rhea 4X: 05.50 fps
4X Slowmo Apollo: 44.50 fps APFast: 75.33 fps Chronos: 33.24 fps CHFast: 39.70 fps
16X Slowmo Aion: 37.31 fps
Here is an AI generated comparison chart of the results (I told the AI to make it playful and it added some funny labels):
1 Like
