# Topaz Video AI 4.2.1.0.b

**URL:** <https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785>\
**Category:** Video AI Beta\
**Created:** [March 8, 2024, 12:11am UTC](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785 "2024-03-08T00:11:12Z")\
**Posts on this page:** 6\
**Page:** 2

<div class="post-metadata">

**Author:** ![jcp29](https://community.topazlabs.com/user_avatar/community.topazlabs.com/jcp29/32/65624_2.png) [@jcp29](https://community.topazlabs.com/u/jcp29)\
**Post date:** [March 11, 2024, 1:58pm UTC](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785/28 "2024-03-11T13:58:50Z")

</div>

I tested with Proteus and Nyx: the estimation works here. Be careful if you change the model, sometimes there is a download of the model (sometimes it’s an update?). It takes time (examining the model storage directory).

![2024-03-11_14-48-33](https://community-cdn.topazlabs.com/original/3X/5/7/57e7c360b5b2af7bb4861f7cbaea64cd21a31029.jpeg)  
 ![2024-03-11_14-49-18](https://community-cdn.topazlabs.com/original/3X/8/d/8dc9fb8ea2420b71d65b9fa85323d50b7d44e1cf.jpeg)  
 ![2024-03-11_14-49-50](https://community-cdn.topazlabs.com/original/3X/8/c/8c514f0e91f44c9482d5fd2db6b72c10ce630bbf.jpeg)  
 ![2024-03-11_14-50-25](https://community-cdn.topazlabs.com/original/3X/0/e/0e473e759324a0077f9e3fd8f287e88db7b1f4d8.jpeg)

On the other hand, I did a test on a 30 minute TL. At the start I have 6 fps and GPU VRAM usage ~10/24 GB, at the end I only have ~3 fps and +23Gb GPU usage (no GPU FULL message). Slow increase in VRAM usage. It seems that there is not enough freeing up of GPU usage. (indications obtained from the Windows control panel).

---

<div class="post-metadata">

**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, 2024, 2:22pm UTC](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785/29 "2024-03-11T14:22:53Z")

</div>

Mine did not change on my Mac .

---

<div class="post-metadata">

**Author:** ![jcp29](https://community.topazlabs.com/user_avatar/community.topazlabs.com/jcp29/32/65624_2.png) [@jcp29](https://community.topazlabs.com/u/jcp29)\
**Post date:** [March 11, 2024, 4:16pm UTC](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785/30 "2024-03-11T16:16:10Z")

</div>

> [@jcp29](#):
>
> sometimes there is a download of the model

I suggest if it is possible that during the download of a model, a popup type information for icon or? is displayed to inform the user to wait.

---

<div class="post-metadata">

**Author:** ![jam7000](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/j/d2c977/32.png) [@jam7000](https://community.topazlabs.com/u/jam7000)\
**Post date:** [March 12, 2024, 2:58am UTC](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785/31 "2024-03-12T02:58:44Z")

</div>

Curious how fast Aion can be with TensorRT acceleration

---

<div class="post-metadata">

**Author:** ![sunday.weaver](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/4da419/32.png) [@sunday.weaver](https://community.topazlabs.com/u/sunday.weaver)\
**Post date:** [March 12, 2024, 2:30pm UTC](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785/32 "2024-03-12T14:30:18Z")

</div>

So apparently THEMIS deblur will be working on RyzenAI / 7000/8000 Mobile NPU, very interesting. Have I missed this feature for releases, or is it a sneak peak sort of deal?

[![](https://img.youtube.com/vi/EvdOQcomG-I/maxresdefault.jpg "4K Motion Deblur using Topaz "Themis" AI Model with Ryzen AI processors.") ](https://www.youtube.com/watch?v=EvdOQcomG-I)

That being said, AMD’s laptop ‘partners’ are very very bad with enabling RyzenAI. I have a Lenovo LOQ 15 7840HS + 4060 laptop, and despite my hardware absolutely having it, Lenovo has not enabled the ‘IPU Device’ despite users giving plenty of requests and feedback to AMD (and other manufacturers) over the past 6 months:

> <https://github.com/amd/RyzenAI-SW/issues/5>
>
> Hi,
> 
> Just purchased a 7940hs based mini pc (GMKTec K4) and I am unable to dete…ct the AMD IPU Device in Device Manager. I have the drivers available and tried installing them, but it looks like the IPU device itself does not exist.
> 
> Looking at the drivers .inf file, it appears to be looking for a device with hardware ID: PCI\\VEN\_1022&DEV\_1502
> 
> I ran \`Get-PnpDevice -PresentOnly | Sort-Object -Property "Class" | Format-Table -AutoSize\` to get all the hardware IDs present on the system and cannot find the hardware ID that IPU Device driver is looking for. See attached output of the command below.
> 
> \[HardwareIDs.txt\](https://github.com/amd/RyzenAI-cloud-to-client-demo/files/12165953/HardwareIDs.txt)
> 
> These are the scenarios coming to my mind:
> 1. There is a mismatch between the driver and the IPU device Hardware IDs. Can someone please share your hardware ID by going to device manager and checking AMD IPU Device properties?
> 3. The IPU device is somehow disabled in the BIOS. Can someone please check if there is a toggle for IPU in the BIOS? The bios on my device is extremely basic and does not allow any advanced config.
> 4. My CPU is missing the IPU device which is extremely odd. One of the main reasons I chose this CPU was to use the IPU device. If this is the case I will have to check with the manufacturer or RMA/return the device.
> 
> Any help will be much appreciated.
> 
> Thank you

---

<div class="post-metadata">

**Author:** ![tony.topazlabs](https://community.topazlabs.com/user_avatar/community.topazlabs.com/tony.topazlabs/32/120833_2.png) [@tony.topazlabs](https://community.topazlabs.com/u/tony.topazlabs)\
**Post date:** [March 14, 2024, 3:45pm UTC](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785/33 "2024-03-14T15:45:17Z")

</div>



[Previous page](https://community.topazlabs.com/t/topaz-video-ai-4-2-1-0-b/64785.md?page=1)
