Topaz Video AI v4.0.4
System Information
OS: Windows v11.22
CPU: AMD Ryzen 9 7950X 16-Core Processor 31.717 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 39.01 fps 2X: 15.43 fps 4X: 03.81 fps
Iris 1X: 37.32 fps 2X: 17.50 fps 4X: 04.89 fps
Proteus 1X: 30.54 fps 2X: 13.87 fps 4X: 03.76 fps
Gaia 1X: 14.78 fps 2X: 10.29 fps 4X: 04.21 fps
Nyx 1X: 16.91 fps 2X: 13.26 fps
4X Slowmo Apollo: 40.63 fps APFast: 71.05 fps Chronos: 29.75 fps CHFast: 33.37 fps
Topaz Video AI v4.0.4
System Information
OS: Windows v11.23
CPU: Intel(R) Core(TM) i9-14900K 63.747 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
GPU: Intel(R) UHD Graphics 770 0.125 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 42.49 fps 2X: 17.33 fps 4X: 04.52 fps
Iris 1X: 39.29 fps 2X: 19.72 fps 4X: 05.25 fps
Proteus 1X: 29.61 fps 2X: 17.85 fps 4X: 04.43 fps
Gaia 1X: 14.43 fps 2X: 09.88 fps 4X: 04.91 fps
Nyx 1X: 16.13 fps 2X: 13.19 fps
4X Slowmo Apollo: 45.00 fps APFast: 75.86 fps Chronos: 31.82 fps CHFast: 34.59 fps
1 Like
Topaz Video AI v4.0.4
System Information
OS: Windows v11.22
CPU: AMD Ryzen 9 7950X 16-Core Processor 63.14 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
GPU: AMD Radeon(TM) Graphics 0.47446 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 46.33 fps 2X: 17.25 fps 4X: 04.63 fps
Iris 1X: 48.13 fps 2X: 20.24 fps 4X: 05.31 fps
Proteus 1X: 44.67 fps 2X: 17.04 fps 4X: 04.52 fps
Gaia 1X: 17.60 fps 2X: 11.86 fps 4X: 04.66 fps
Nyx 1X: 18.54 fps 2X: 15.86 fps
4X Slowmo Apollo: 42.40 fps APFast: 77.75 fps Chronos: 33.61 fps CHFast: 34.36 fps
Would it be possible to have all these results plotted into a graph, showing performance ranges for each model/configuration? maybe pick a few common configurations to begin withâŠ
This would help purchase decisions for new systems or upgrades.
Thanks!
2 Likes
This is not a easy task.
CPU, GPU, RAM (DDR4/DDR5 ram speed & timing),
Some users has overclocked their CPU & GPU,
while some users has limited the TDP or undervolt.
The variation can be huge, even they have the same CPU & GPU.
1 Like
running on M2 macbook is very slow, sometimes 0.5fps only. Is it normal?
I completely understand (built many PCs until I switched to Mac). Still, I can see 2 potential outcomes
- obtain directional information (not perfect) that can help people make hardware choices
- better understand what hardware change impacts the performance of video processing (this will take more time)
Thanks for the feedback!
2 Likes
With Iris, yes. This is slower than need be on Apple Silicon especially with the 2x upscale model.
Still, 0.5 fps seems a bit low except if you are upscaling to 4k?
Topaz Video AI v4.0.4
System Information
OS: Windows v10.22
CPU: AMD Ryzen 9 5950X 16-Core Processor 31.926 GB
GPU: NVIDIA GeForce RTX 3080 Ti 11.816 GB
Processing Settings
device: -2 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 25.49 fps 2X: 12.00 fps 4X: 03.22 fps
Iris 1X: 24.37 fps 2X: 13.84 fps 4X: 03.89 fps
Proteus 1X: 22.52 fps 2X: 11.11 fps 4X: 03.14 fps
Gaia 1X: 08.78 fps 2X: 06.01 fps 4X: 03.31 fps
Nyx 1X: 10.48 fps 2X: 08.69 fps
4X Slowmo Apollo: 34.02 fps APFast: 59.23 fps Chronos: 19.69 fps CHFast: 26.90 fps
Windows 11 debloated
No Antivirus or cleaner programs
Asus Z790
I have four onboard Nvme 4th gen drives
Boot drive
Cache drive
Media drive
Mixdown drive
Liquid cooled
4090 drivers 546.01 studio drivers
Topaz Video AI v4.0.4
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: 168.28 fps 2X: 77.45 fps 4X: 21.85 fps
Iris 1X: 183.83 fps 2X: 113.53 fps 4X: 29.55 fps
Proteus 1X: 147.19 fps 2X: 70.43 fps 4X: 21.30 fps
Gaia 1X: 88.75 fps 2X: 61.81 fps 4X: 26.10 fps
Nyx 1X: 51.25 fps 2X: 48.27 fps
4X Slowmo Apollo: 225.41 fps APFast: 540.05 fps Chronos: 166.54 fps CHFast: 204.24 fps
Topaz Video AI v4.0.4
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: 40.90 fps 2X: 15.59 fps 4X: 04.14 fps
Iris 1X: 33.13 fps 2X: 18.97 fps 4X: 05.22 fps
Proteus 1X: 35.16 fps 2X: 14.35 fps 4X: 04.06 fps
Gaia 1X: 15.72 fps 2X: 10.83 fps 4X: 04.43 fps
Nyx 1X: 17.62 fps 2X: 14.60 fps
4X Slowmo Apollo: 44.99 fps APFast: 75.29 fps Chronos: 33.44 fps CHFast: 34.68 fpsTopaz Video AI v4.0.4
System Information
OS: Windows v11.23
CPU: AMD Ryzen 7 7800X3D 8-Core Processor 31.117 GB
GPU: AMD Radeon RX 6800 XT 15.954 GB
Processing Settings
device: 0 vram: 1 instances: 0
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 12.53 fps 2X: 07.80 fps 4X: 02.47 fps
Iris 1X: 13.53 fps 2X: 07.65 fps 4X: 02.48 fps
Proteus 1X: 11.88 fps 2X: 07.48 fps 4X: 02.44 fps
Gaia 1X: 05.86 fps 2X: 03.97 fps 4X: 02.61 fps
Nyx 1X: 05.11 fps 2X: 04.26 fps
4X Slowmo Apollo: 19.40 fps APFast: 48.26 fps Chronos: 07.87 fps CHFast: 14.10 fps
I've undervolted 1080mV and underclocked (2250Mhz) my 6800XT to reduce power usage from 330W to ~250W
1 Like
Impressive but still not fast enough given the configuration
Any suggestions on configuration ?
Topaz Video AI v4.0.3
System Information
OS: Windows v10.22
CPU: AMD Ryzen 7 5800X3D 8-Core Processor 63.912 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
GPU: NVIDIA GeForce RTX 4090 23.59 GB
Processing Settings
device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 30.27 fps 2X: 12.96 fps 4X: 03.34 fps
Iris 1X: 37.95 fps 2X: 13.83 fps 4X: 03.71 fps
Proteus 1X: 26.25 fps 2X: 10.53 fps 4X: 03.15 fps
Gaia 1X: 15.40 fps 2X: 10.45 fps 4X: 03.12 fps
Nyx 1X: 16.95 fps 2X: 13.26 fps
4X Slowmo Apollo: 36.54 fps APFast: 69.10 fps Chronos: ... fps CHFast: - fps
This software seems really not optimized ! Itâs incredible that you have not better performances with a such powerful computer !
Topaz Video AI v4.0.4
System Information
OS: Mac v12.0701
CPU: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz 32 GB
GPU: AMD Radeon R9 M395X 4 GB
Processing Settings
device: 0 vram: 0.75 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 00.94 fps 2X: 00.61 fps 4X: 00.22 fps
Iris 1X: 00.71 fps 2X: 00.35 fps 4X: 00.12 fps
Proteus 1X: 00.78 fps 2X: 00.53 fps 4X: 00.22 fps
Gaia 1X: 00.25 fps 2X: 00.18 fps 4X: 00.14 fps
Nyx 1X: 00.36 fps 2X: 00.32 fps
4X Slowmo Apollo: 00.80 fps APFast: 03.46 fps Chronos: 00.24 fps CHFast: 00.45 fps
The numbers are ok if you consider that the M3 Max has 20 Teraflops fp32.
Comparable to RX 6800 XT bc it has 20 TF too.
RTX 4090 has 82 Teraflops.
You oversaw the Iris 2x numbers (which I guess is the most widely used model and upscale factor)? And Iris performance in general which is roughly comparable to Proteus on NVidia, AMD and even integrated Intel GPUs, just not on Apple Silicon.
Those numbers definitely arenât OK for Iris performance - and we also do know from the past that Iris could generally be nearly 2x faster, for the 2x upscale model more like 4 times faster.
2 Likes
Apple seems very closed when it comes to their hardware. To get maximum performance, you would probably need to create a new version of the application that uses all their building tools.
There are software developers on my team that got M1 Macs when they came out. There are still development tools we use that just donât work the same on M1. Theyâve had several years to fix that now. Either it must be really hard, or not possible.
But this doesnât really apply to TVAI.
We already had faster Iris speeds but there was a conflict with the early Sonoma versions and TVAI 3.4 upwards leading to a garbage output.
The fix Topaz applied for that came with a drastic performance loss especially for the (most used) x2 upscale model.
Just that now with Sonoma 14.1 (and 14.2) this old fast models in fact work flawlessly again at least here on two different configs (M1 Pro and M2 Ultra) without visual flaws but better performance.
Plus, even accepting the low performance TVAI doesnât really scale well with multiple GPU cores. My M2 ultra with 60 GPU cores is only up to about 2.5 times than the M1 Pro with 16 cores.
(P.S.: The not so well scaling of TVAI with multiple cores / higher GPU performance partly can also be seen on NVidia).
1 Like
