Hello everyone,
is there any way to speed up the upscaling process?
I am running Topaz Video Enchance AI version 2.6.3 on a:
AMD Ryzen 5 3600x
32 GB DDR 3200 RAM
Gigabyte Radeon™ RX 6800 XT GAMING OC 16G
Yes. Process the video to images. Run a second instance of VE AI and let both work simoultanously on seperate parts of the video, maybe one working on the first half of the video and the other one on the second half. 
1 Like
That sounds like a good idea, is there a tutorial or guide for this suggestion?
- Just find the best settings you want to process the video
- Save it in a preset on the top right of the VE AI menu
- Look at the total number of frames below the video.
- Devide it by two.
- Choose .jpg output on the lower right of VE AI
- Start processing the frames zero to half of all.
- Open a second instance of VE AI by holding SHIFT when double clicking VE AI.
- Now move the time line slider to avoid a minor bug that resets the choosen model
- Select the saved preset from the top right again.
- Type in to process the frames half-of-all+1 to end of the video below the time line
- Start processing.
- Now put another window in front of these two VE AI to make them run simoultanously at the same speed; otherwise the VE AI in the front will get more processing power and the one in the back less.
Can i request a video how to do this speedup.
1 Like
I there a more updated version to this process?
No. I think it still works that way. If it doesn’t just let me know. I will then look closer into it to make a new video!
Wry much appreciated. One more question can it be video format instead of Image?
For example, mov or mp4 instant of png?
Yes of course. In this case you must put together the video parts with a tool of your choice when the processing finished.
Tip: don’t render out JPEG’s. They’re lossy files and introduce even more noise and distortion. Otherwise it’s a great workflow!
