# Topaz Video AI Performance Alpha 3.2.0.1.a **URL:** \ **Category:** Video AI Beta\ **Created:** [March 10, 2023, 10:56pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420 "2023-03-10T22:56:43Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![suraj](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/ecccb3/32.png) [@suraj](https://community.topazlabs.com/u/suraj)\ **Post date:** [March 10, 2023, 10:56pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/1 "2023-03-10T22:56:43Z")
Hi All, Here is an early version of app that should improve performance for all machines. The degree of performance increase will vary. This version should also allow for better support running multiple filters and multiple processes. Download: [Win](https://downloads.topazlabs.com/deploy/TopazVideoAIAlpha/3.2.0.1.a/TopazVideoAIAlpha-3.2.0.1.a.msi) | [Mac](https://downloads.topazlabs.com/deploy/TopazVideoAIAlpha/3.2.0.1.a/TopazVideoAIALPHA-3.2.0.1.a.dmg) | [Mac Update](https://downloads.topazlabs.com/deploy/TopazVideoAIAlpha/3.2.0.1.a/TopazVideoAIALPHA-3.2.0.1.a.pkg) Please upload problem videos and logs here: [Submit Files](https://www.dropbox.com/request/hxLNzpT1g3nsCHG4iM2E) **Changes from 3.2.0.0.a** - [Benchmarking support](https://community.topazlabs.com/t/performance-benchmarking/41416) - GUI updates from v3.1.9.0.b **Known Issues** : - Proteus Auto will not work, use Proteus with manual settings - Running stabilization may cause failures - No way to boost performance if running single filter or process Thank you for testing PS: Since this is an alpha version, it will not interfere with Beta or Release versions on the machine. ---
**Author:** ![suraj](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/ecccb3/32.png) [@suraj](https://community.topazlabs.com/u/suraj)\ **Post date:** [March 10, 2023, 10:58pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/2 "2023-03-10T22:58:10Z")
---
**Author:** ![avid-1676](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/e19adc/32.png) [@avid-1676](https://community.topazlabs.com/u/avid-1676)\ **Post date:** [March 11, 2023, 12:09am UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/3 "2023-03-11T00:09:45Z")
I have tried a few different files, none of them seem to work. I get “Unknown Error” on all of them right after seeing “Model Loaded”. Log attached. [2023-03-10-17-54-45-Main.tzlog.txt](https://community.topazlabs.com/uploads/short-url/bWXtdTUC1mpubB2C5Q94uXF2sX3.txt) (460.3 KB) ---
**Author:** ![suraj](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/ecccb3/32.png) [@suraj](https://community.topazlabs.com/u/suraj)\ **Post date:** [March 11, 2023, 12:39am UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/4 "2023-03-11T00:39:52Z")
Proteus auto/relative to auto and estimate are currently not supported. Use manual parameters if using proteus. ---
**Author:** ![avid-1676](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/e19adc/32.png) [@avid-1676](https://community.topazlabs.com/u/avid-1676)\ **Post date:** [March 11, 2023, 12:52am UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/5 "2023-03-11T00:52:17Z")
Apologies for not seeing that in the notes. ---
**Author:** ![vincent.courtois](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/v/bcef8e/32.png) [@vincent.courtois](https://community.topazlabs.com/u/vincent.courtois)\ **Post date:** [March 11, 2023, 1:07am UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/6 "2023-03-11T01:07:09Z")
Hi Suraj, I just downloaded your Topaz Video AI Performance Alpha 3.2.0.1.a and performed few tests with an old CGI from the 1970s. First review: 1. Speed rendering is 3x to 4x faster ; 2. Picture quality is very good and most of visual artifacts are gone ; 3. Some visual artefacts can be seen as echoes : for instance in a sky with fast moving clouds (timelapse), you can see some echoes around the clouds in the sky ; Maybe not visual artefacts, just hidden motion blur revealed by super resolution engine ; 4. I used Proteus Fine without Auto mode, with manual settings as suggested ; What is missing: 1. Auto color correction ; 2. Auto dust removal (for old dusty footage) ; 3. A way to declare some frames as defective, so to avoid them and interpolate from previous to next legitimate ones ; i.e. a video footage with missing frames or badly recorded frames (very old 2 inches video tapes) ; 4. Zoom / Zoom mode settings lost each time I switch between Main mode and Preview mode ; 5. A video drop out removal filter for old video footage like U-Matic, VHS, Super-VHS, Beta, and so on ; 6. A temporary licence key for user as me that have not current licence. I am using Trial mode, better for seeing the output picture quality ; 7. Auto color expander ; Color noise reduction ; Looks ; like Topaze Adjust AI. Globaly a very good version anyway. Kind regards. Vincent. ---
**Author:** ![alanhusband-677420](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/7ba0ec/32.png) [@alanhusband-677420](https://community.topazlabs.com/u/alanhusband-677420)\ **Post date:** [March 11, 2023, 4:12am UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/7 "2023-03-11T04:12:22Z")
On my GTX 1060 the new alpha is faster than the new beta across all models benchmarked using single processes (I think Gaia 4X errors because it hits a vram limit): Topaz Video AI Beta v3.1.9.0.b System Information OS: Windows v10.2009 CPU: AMD Ryzen 7 2700X Eight-Core Processor 15.939 GB GPU: NVIDIA GeForce GTX 1060 6GB 5.9014 GB Settings: device: 0 vram: 1 instances: 0 Benchmark Results Artemis 1X: 1.42 fps 2X: 0.89 fps 4X: 0.34 fps Proteus 1X: 1.26 fps 2X: 0.85 fps 4X: 0.34 fps Gaia 1X: 0.55 fps 2X: 0.38 fps 4X: ERR fps 4X Slowmo Apollo: 2.06 fps Chronos: 0.87 fps Chronos Fast: 1.47 fps Topaz Video AI Alpha v3.2.0.1.a System Information OS: Windows v10.2009 CPU: AMD Ryzen 7 2700X Eight-Core Processor 15.939 GB GPU: NVIDIA GeForce GTX 1060 6GB 5.9014 GB Settings: device: 0 vram: 1 instances: 0 Benchmark Results Artemis 1X: 1.67 fps 2X: 1.14 fps 4X: 0.46 fps Proteus 1X: 1.61 fps 2X: 1.1 fps 4X: 0.45 fps Gaia 1X: 0.59 fps 2X: 0.4 fps 4X: ERR fps 4X Slowmo Apollo: 2.29 fps Chronos: 0.92 fps Chronos Fast: 1.53 fps ---
**Author:** ![karol.guzik](https://community.topazlabs.com/user_avatar/community.topazlabs.com/karol.guzik/32/78468_2.png) [@karol.guzik](https://community.topazlabs.com/u/karol.guzik)\ **Post date:** [March 11, 2023, 8:17am UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/8 "2023-03-11T08:17:38Z")
![image](https://community-cdn.topazlabs.com/original/3X/0/5/05b59eb53d495edc16bf4367e0dee5b82c1bf71b.png) Topaz Video AI Alpha v3.2.0.1.a System Information OS: Windows v11.2009 CPU: AMD Ryzen 9 7950X 16-Core Processor (eco mode 65W) 31.118 GB GPU: NVIDIA GeForce RTX 4090 23.59 GB (60% power limit) Settings: device: 0 vram: 0.9 instances: 0 Benchmark Results Artemis 1X: 33.29 fps 2X: 16.17 fps 4X: 4.35 fps Proteus 1X: 26.94 fps 2X: 15.32 fps 4X: 4.4 fps Gaia 1X: 14.77 fps 2X: 9.74 fps 4X: 4.94 fps 4X Slowmo Apollo: 18.31 fps Chronos: 29.48 fps Chronos Fast: 38.07 fps \*\*And oh this is the results as TOPAZ AI is in the background. \*\* **It gets completely different results in Apollo model.** ![image](https://community-cdn.topazlabs.com/original/3X/b/d/bddbfe69bc647205cafe943f68feb820c9a9a7e0.png) Artemis 1X: 32.76 fps 2X: 15.98 fps 4X: 4.44 fps Proteus 1X: 28.56 fps 2X: 14.52 fps 4X: 4.35 fps Gaia 1X: 15.15 fps 2X: 9.86 fps 4X: 5.06 fps 4X Slowmo Apollo: 23.22 fps Chronos: 29.95 fps Chronos Fast: 37.26 fps ---
**Author:** ![topaz257](https://community.topazlabs.com/user_avatar/community.topazlabs.com/topaz257/32/129593_2.png) [@topaz257](https://community.topazlabs.com/u/topaz257)\ **Post date:** [March 11, 2023, 11:05am UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/9 "2023-03-11T11:05:00Z")
Great to have a built-in benchmark! When I have some more time I will check RAM speed scaling, which is usually not very much discussed. I suspect RAM speed could have some influence on processing with image scaling. 7950 + 4090 + 6400 RAM @ CL30 + Win10 This is with an overlock of the **GPU @ 3000 Mhz @ 300W avg (peak 450W)** ![image](https://community-cdn.topazlabs.com/original/3X/9/7/976531785ff76af67420bc3ea6caa2ecddacf907.png) | Artemis | | 1X: 36.9 fps | 2X: 17.98 fps | 4X: 5.29 fps | | | --- | --- | --- | --- | --- | --- | | Proteus | | 1X: 31.55 fps | 2X: 16.72 fps | 4X: 5.14 fps | | | Gaia | | 1X: 14.81 fps | 2X: 9.38 fps | 4X: 5.25 fps | | | 4X Slowmo | | Apollo: 26.85 fps | Chronos: 31.48 fps | Chronos Fast: 42.31 fps | | This is with **GPU @ 2115 Mhz @ 0.875v @ 200W avg (peak 300W)** ![image](https://community-cdn.topazlabs.com/original/3X/1/6/1692e90030b8716bf4b991609aad0b2f97081d9c.png) | Artemis | | 1X: 32.6 fps | 2X: 17.34 fps | 4X: 5.08 fps | | | --- | --- | --- | --- | --- | --- | | Proteus | | 1X: 29.8 fps | 2X: 15.39 fps | 4X: 4.86 fps | | | Gaia | | 1X: 13.63 fps | 2X: 8.86 fps | 4X: 4.77 fps | | | 4X Slowmo | | Apollo: 26.33 fps | Chronos: 26.54 fps | Chronos Fast: 38.81 fps | | It’s interesting to see that some models profit much more from GPU speed than others. Chronos scales the best, thereas Artemis, Proteus and Gaia scale only half as much. And especially at higher scaling factors, CPU + RAM seems to be more and more the limiting factor. ---
**Author:** ![karol.guzik](https://community.topazlabs.com/user_avatar/community.topazlabs.com/karol.guzik/32/78468_2.png) [@karol.guzik](https://community.topazlabs.com/u/karol.guzik)\ **Post date:** [March 11, 2023, 12:15pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/10 "2023-03-11T12:15:56Z")
I updated my result that I use eco mode for CPU and GPU. Were you using the CPU on standard settings or limiting its power access? And mem settings. ![image](https://community-cdn.topazlabs.com/original/3X/d/e/de1b1214061ba0e116fb64c834e59ad760e87545.png) ---
**Author:** ![menthurae](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/m/848f3c/32.png) [@menthurae](https://community.topazlabs.com/u/menthurae)\ **Post date:** [March 11, 2023, 1:21pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/12 "2023-03-11T13:21:17Z")
Oops - posted as a reply to the wrong person/not to the main thread. I’m getting flickering grey frames constantly with this build - same settings and it’s fine in 3.1.9.0b. RTX A4000, NVIDIA 531.18 ---
**Author:** ![overlord\_chaos11](https://community.topazlabs.com/user_avatar/community.topazlabs.com/overlord_chaos11/32/67660_2.png) [@overlord\_chaos11](https://community.topazlabs.com/u/overlord_chaos11)\ **Post date:** [March 11, 2023, 1:30pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/13 "2023-03-11T13:30:31Z")
speed is pretty much the same for me as regular/beta but i run an old episode of an old 2000 tv show and the output is nightmare fuel. skin that seems to melt off the face of the actor/actresses, eyes that warp in size and position as well as moles on the skin. hair that frame by frame goes from low quality to normal to HD crisp to look like wood chip strings… even that i may set up the proteus manually too high, the AI clearly lost its mind since its nightmare fuel. its so distracting from minutes to minutes i forgot what i was watching seeing the face of a person “melting down” and becoming all wrinkled and bended/warped also did a benchmark on my system ![image](https://community-cdn.topazlabs.com/original/3X/0/2/02b7adc216c00fb55c8a885712eb5087f9fbc36a.png) ---
**Author:** ![admpodg](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/a/b2d939/32.png) [@admpodg](https://community.topazlabs.com/u/admpodg)\ **Post date:** [March 11, 2023, 1:42pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/14 "2023-03-11T13:42:19Z")
I have stupid question, but anyway I will ask - I haven’t been using Topaz for a long time because I was busy with other task, but when I saw an email with new alpha, I did not hesitate to download it and test - but then the pop-up with expired license showed up - it is really neccessery for alpha/beta tester to buy upgrade? ---
**Author:** ![johnnystar](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/e47c2d/32.png) [@johnnystar](https://community.topazlabs.com/u/johnnystar)\ **Post date:** [March 11, 2023, 1:47pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/15 "2023-03-11T13:47:28Z")
I hope this version will give AMD gpu’s on Mac some love. ---
**Author:** ![JesusSheep](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/ec9cab/32.png) [@JesusSheep](https://community.topazlabs.com/u/JesusSheep)\ **Post date:** [March 11, 2023, 2:54pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/16 "2023-03-11T14:54:12Z")
@suraj Can you add support for all GPUs EGPUs and Internal to run at same time on Macs ? Topaz Video AI Alpha v3.2.0.1.a System Information OS: Mac v13.0201 CPU: Intel(R) Core™ i5-7600K CPU @ 3.80GHz 32 GB GPU: AMD Radeon Pro 580 8 GB Settings: device: 0 vram: 1 instances: 1 Benchmark Results Artemis 1X: 1.39 fps 2X: 0.96 fps 4X: 0.4 fps Proteus 1X: 1.53 fps 2X: 1.07 fps 4X: 0.46 fps Gaia 1X: 0.52 fps 2X: 0.37 fps 4X: 0.29 fps 4X Slowmo Apollo: 1.51 fps Chronos: 0.21 fps Chronos Fast: 0.46 fps ![Screenshot 2023-03-11 at 7.22.28 AM](https://community-cdn.topazlabs.com/original/3X/1/8/1893ab404d357ea133adf076002b78dd5a71d3b6.jpeg) ---
**Author:** ![tom-103590](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/t/ccd318/32.png) [@tom-103590](https://community.topazlabs.com/u/tom-103590)\ **Post date:** [March 11, 2023, 5:26pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/17 "2023-03-11T17:26:55Z")
Here are the benchmark results on my M1 Max MacBook Pro: Topaz Video AI Alpha v3.2.0.1.a System Information OS: Mac v13.0201 CPU: Apple M1 Max 64 GB GPU: Apple M1 Max 48 GB Settings: device: 0 vram: 1 instances: 1 Benchmark Results Artemis 1X: 8.16 fps 2X: 5.49 fps 4X: 2.35 fps Proteus 1X: 8.13 fps 2X: 5.94 fps 4X: 1.87 fps Gaia 1X: 2.65 fps 2X: 1.83 fps 4X: 1.47 fps 4X Slowmo Apollo: 8.63 fps Chronos: 2.75 fps Chronos Fast: 4.26 fps Using Dione Robust to process a 720 X 480 progressive interlaced video to HD gave the fastest result Ihave yet obtained of 0.05 sec/frame. Great job on this Alpha! ---
**Author:** ![topaz257](https://community.topazlabs.com/user_avatar/community.topazlabs.com/topaz257/32/129593_2.png) [@topaz257](https://community.topazlabs.com/u/topaz257)\ **Post date:** [March 11, 2023, 6:22pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/18 "2023-03-11T18:22:37Z")
I was using ECO mode on CPU which limits the 7950X to 140W but that is never reached during the benchmark. For limiting the GPU, I use MSI Afterburner with a custom voltage/speed curve: ![image](https://community-cdn.topazlabs.com/original/3X/5/9/59c0f4ec3a27800085e4becc5258220a272661a1.png) RAM settings (custom tuned) ![image](https://community-cdn.topazlabs.com/original/3X/c/0/c012166009d3fd4bb98cc60b8f0fca6b21006dbb.png) Expo settings ![image](https://community-cdn.topazlabs.com/original/3X/6/7/67f977992a6a8c28a78728d8e696fced135c6160.png) ---
**Author:** ![johnnystar](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/e47c2d/32.png) [@johnnystar](https://community.topazlabs.com/u/johnnystar)\ **Post date:** [March 11, 2023, 6:33pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/19 "2023-03-11T18:33:08Z")
It already works for me with RX6800XT egpu and Radeon Pro 575 internal. ---
**Author:** ![JesusSheep](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/ec9cab/32.png) [@JesusSheep](https://community.topazlabs.com/u/JesusSheep)\ **Post date:** [March 11, 2023, 6:51pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/20 "2023-03-11T18:51:00Z")
Topaz Video AI Alpha v3.2.0.1.a System Information OS: Windows v10.2009 CPU: Intel(R) Core™ i7-7700HQ CPU @ 2.80GHz 15.957 GB GPU: NVIDIA GeForce GTX 1060 5.9014 GB Settings: device: 0 vram: 1 instances: 0 Benchmark Results Artemis 1X: 0.07 fps 2X: 0.05 fps 4X: 0.04 fps Proteus 1X: 0.11 fps 2X: 0.08 fps 4X: 0.04 fps Gaia 1X: 0.04 fps 2X: ERR fps 4X: ERR fps 4X Slowmo Apollo: ERR fps Chronos: 0.26 fps Chronos Fast: ERR fps Topaz Video AI Alpha v3.2.0.1.a System Information OS: Mac v13.0201 CPU: Intel(R) Core™ i5-7600K CPU @ 3.80GHz 32 GB GPU: AMD Radeon RX 480 8 GB GPU: AMD Radeon Pro 580 8 GB Settings: device: 2 vram: 1 instances: 1 Benchmark Results Artemis 1X: 2.45 fps 2X: 1.62 fps 4X: 0.65 fps Proteus 1X: 2.83 fps 2X: 1.83 fps 4X: 0.77 fps Gaia 1X: 1.01 fps 2X: 0.71 fps 4X: 0.54 fps 4X Slowmo Apollo: 2.55 fps Chronos: 0.29 fps Chronos Fast: 0.67 fps I can reduce the 720p ---
**Author:** ![johnnystar](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/e47c2d/32.png) [@johnnystar](https://community.topazlabs.com/u/johnnystar)\ **Post date:** [March 11, 2023, 8:30pm UTC](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420/21 "2023-03-11T20:30:56Z")
Just curious, what is the resolution of the source video, since that makes a huge difference? [Next page](https://community.topazlabs.com/t/topaz-video-ai-performance-alpha-3-2-0-1-a/41420.md?page=2)