Search results
29 mar 2022 · 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.
Run two instances & output to png. Hold shift when opening to open the second instance of topaz and set the in and out markers to the front half in one and the second half in the other. i have a gt730 and a i7 9700 and for a 10 sec video upscale it takes 2h. The latest version of VE AI utilizes GPUs much better now.
11 sie 2023 · Based on what your source is, and they amount of work to upscale to 4K 60fps, I6-7 fps sounds right. You either need a 40 series card, or i9, or both, to get better speed.
17 mar 2021 · Even though the clip was only 31 seconds long, it took about 3 hours to render! By comparison, upgrading to HD only took about 45 minutes. I’m not going to bash VEAI, as it worked as expected. At least it didn’t crash. I set my “Max VRAM Usage” to Medium/Low, as per Topaz’s recommendation.
Too slow, especially if you come from an ffmpeg / Cuda encoding environment. As far as I can tell it seems to encode the video using the cpu and uses the gpu as a very fast ram to store the image data. I saw very little improvement after buying a rtx 3060 compared to cpu intel graphics.
So you are pushing 16x the amount of pixel of fullhd videos. That will take ages and even if the encoder is hardware optimized to encode the video to a certain format, the way the AI encoder works it won't get much faster as you are simply pushing too high a resolution.
Get started in Topaz Studio for free. Download Topaz Studio We use the most advanced developments in imaging technology to create powerful software products for photographers.
