Topaz Video AI Legacy

We built Topaz Video AI v3.0 from the ground up to include new functionality, such as video stabilization, improved enhancement capabilities, and a better user experience. Using this new code base allows us to provide some of your most requested features, such as:

  • Stacking AI models
  • Running tasks in parallel with filter support
  • Command-line interface
  • Important performance and stability improvements

This page contains important information for users working with the previous Video Enhance AI v2:

What is Video Enhance AI?

Using the power of machine-learning AI technology, Video Enhance AI is trained on thousands of videos and combines information from multiple input video frames. It can enlarge your video up to 8k resolution with true details and motion consistency. For example, you can upscale SD video to HD or even 4K resolution.

What is the minimum hardware requirement for Video Enhance AI?

A DirectX12 compatible GPU (NVIDIA or AMD). An Intel CPU from 2015 onwards or an AMD CPU from 2016 onwards are our minimum requirements for the CPU.

Mac minimum requirements: 8GB or more RAM, 2GB of VRAM. MacOS 10.14 (Mojave) to run on CPU only. MacOS 10.15 (Catalina) or newer to run on GPU. This gives the best performance.
Full M1 native support for all M1 machines in version 2.5 and higher.

Can Video Enhance AI work on Macs?

Yes. Video Enhance AI can run on all Mac models that meet the hardware requirements from 2012 onwards including M1 machines.

Can I buy one and run it on both Mac and Windows?

Yes, your license exists independently of your operating system.

Can I do batch processing on several videos?

Sure you can! You can load several videos simultaneously into Video Enhance AI. All of them can be assigned with different settings including output size, upsample scale, output format, model utilized and etc. Then with a single click on the process button, they will all be processed in sequence.

How long will it take to process a video?

Here is an example. On a PC with NVIDIA GTX 1080. For a video from HD to 8K, it typically takes 2-3 seconds for each frame. If you upscale a video from SD to HD, it will take about 0.4 seconds for each frame.

What is the maximum size of an output video I can get?

We support up to 8K video output. Any size larger than 8K will cause a failure. But you can set the output format as a sequence of images (png/tif/tiff) which can support nearly any size.

What is the maximum size of an output video I can process?

We support up to 8K video output. Any size larger than 8K will cause a failure. But you can set the output format as a sequence of images (png/tif/tiff) which can support nearly any size.

Can I process interlaced Video?

Yes! You will want to use our Dione models to deinterlace.

My machine has more than one Nvidia GPU, can I use all of them?

Yes, you can use the Experimental All GPU option.

The Experimental All GPU setting is intended for users with multiple similar Nvidia or AMD GPUs installed (it will not work for Intel GPUs). For example, if you have two NVidia RTX 2080 cards installed or one GTX 1070 and one RTX 2080, this setting is for you. If you have a dedicated GPU and an integrated Intel GPU, you should choose your dedicated GPU, the All GPUs setting may not work for you or perform more slowly. To enable both graphics cards you would want to select Preferences from the Video Enhance AI menu and change the AI Processor to All GPUs. VEAI can only use 8-1 2 GB of VRAM in one instance, and can’t consume more than this at this time, you can launch VEAI again on a windows machine and that will allow the second instance to consume more. We are working on optimizations to use all ram

Can I read a sequence of images as input?

Yes. You can put a sequence of images of the same name format into one folder and then load in any one of the images into Video Enhance AI. Please make sure that the name of the images should end with several sequential number digits. An example: MyFrames000000.png, MyFrames000001.png, MyFrames000002.png, ...

My GPU utilization seems low in the task manager. Is there something wrong?

This is normal. The GPU utilization in the task manager is not precise. If you want to track the actual GPU usage, please try Nvidia-smi. You can also increase the amount of GPU usage in the app by going to Process > Preference and increasing the AI Resources Demand

For Mac M1: The M1 chip has a built-in Neural Engine. The Neural Engine is designed to accelerate machine learning tasks across the Mac for things like video analysis, voice recognition, image processing, and more. Right now you will not be able to accurately track CPU or GPU usage.

Can I try Video Enhance AI before buying it?

First, if you are new to Topaz Labs, create an account on the Topaz Labs My Account Page. Next, simply download Video Enhance AI from the Topaz Labs Downloads Page, (https://topazlabs.com/downloads/) log in using your account information, and select "Start Trial" to begin your free 30-day trial.

Can I assume the Mac and Windows versions deliver identical results?

No. This is a difficult computer science problem to solve, but we do our best to make the results nearly identical. Whenever possible. If you do notice any aberrations between operating systems, please Open a Ticket in the Support Center (https://support.topazlabs.com/).

What file types are compatible with Video Enhance AI?

Video Enhance AI is compatible with the following file types:

Video: .avi, .dv, .flv, .m1v, .mkv, .mov, .mp4, .mpg, .mpeg, .mxf, .ts, .vob, .webm, .wmv

Image: .jpg, .jpeg, .png, .tif, .tiff

Sharpen AI

Plugins