Frequently Asked Questions for Topaz Video AI v3.0

Table of Contents

What is the difference between Video Enhance AI (VEAI) & Topaz Video AI (TVAI)?

After reviewing the list of pain points our users experienced in VEAI, as well as the feature requests that were received, it became clear that VEAI had to change significantly to evolve into a product enjoyed by both beginners, and experts alike. 

Most of the issues stemmed from the fact video was being treated as a series of constant-rate images. All the current models operate on this assumption and as a result, had issues processing videos with variable frame rates, repeated frames, scene changes, etc. This was hampering the development of new models and processes that require multiple passes, like stabilization, scene detection, etc. To address these concerns and allow the addition of new features, we decided to rewrite the code base.

This approach allows us to focus on our core expertise to create and improve our models to perform better on all user videos.

Topaz Video AI consists of two independent parts: the Graphical user interface (GUI) and the backend FFmpeg filters. The GUI will merely call the FFmpeg backend and spawn separate processes. Topaz Video AI v3 unveiled a Stabilization model that allows users to stabilize their videos and keep the original resolution.

What is the minimum hardware requirement for Topaz Video AI?

Windows Minimum Requirements: A DirectX12 compatible GPU (NVidia or AMD). An Intel CPU from 2015 onwards or an AMD CPU from 2016 onwards. A dedicated GPU with at least 4GB of VRAM.

Mac Minimum Requirements: 16GB or more RAM, 2GB of VRAM. MacOS 10.14 (Mojave) or 10.15 (Catalina) to run on CPU only. MacOS 10.16 (Big Sur) or newer to have all models run on GPU. This gives the best performance.  Our apps support M1 processors natively. 

How do I get Topaz Video AI?

Any user who currently owns an active upgrade license for Video Enhance AI will be able to update to this new build. New user? Head over to our Shop page to purchase TVAI. 

Can I chain or use more than one model at the same time?

You can use more than one filter in the same processing task in Topaz Video AI. 

Do you have instructions on how to use Command Line Interface (CLI) in Topaz Video AI?

You can access our Command Line Interface (CLI) documentation by clicking here.

Can I build my own FFmpeg with additional features and your AI filters & models?

Yes, you can download redistributable files to build your own FFmpeg with additional features + our AI filters and models. These files are intended to allow advanced users to build FFmpeg with additional features + our AI filters. For most use-cases, the regular installation package will suffice.

You can download the most recent redistributables here. 

Did this answer your question? Thanks for the feedback There was a problem submitting your feedback. Please try again later.