Video Roadmap Update (April 2023)

Product Updates

We’re proud to offer a significant boost in performance and better-synced previews since our last roadmap update.

Large performance gains from CPU/GPU usage optimization

Depending on your selected model and hardware configuration, you will now be able to preview and export 50-100% faster since a month ago. Here’s a few real-world examples based on our testing:

Themis (Motion Deblur) also now uses TensorRT on supported GPUs, and we’ve also made additional performance improvements for the Stabilization filter. These are all on top of the already-significant engine optimizations from January.

To easily test performance on your own computer, you can also now select the new Process → Benchmark feature in the Topaz Video AI menu. Note that benchmarks only measure processing performance and does not include time spent encoding or writing, so benchmark results will be faster than actual output. We also recommend setting Preferences → Max Processes to 1 for the most accurate results. Here’s an example:

Topaz Video AI  v3.2.2
System Information
OS: Mac v13.02
CPU: Apple M1 Max  32 GB
GPU: Apple M1 Max  21.333 GB
Processing Settings: device: 0 vram: 1 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis		1X: 8.42 fps 	2X: 5.53 fps 	4X: 2.19 fps 	
Proteus		1X: 8.67 fps 	2X: 5.45 fps 	4X: 1.86 fps 	
Gaia		1X: 2.62 fps 	2X: 1.96 fps 	4X: 1.50 fps 	
4X Slowmo		Apollo: 7.44 fps 	Chronos: 2.96 fps 	Chronos Fast: 5.11 fps 	

You can compare your results with previous versions of Topaz Video AI, or easily see how it stacks up with other users in v3.2 Benchmarking Results. We’ll continue optimizing the software and models in the future, but we hope you enjoy the faster speeds in the meantime.

Better synced previews

In the past few months we built an upgraded in-app video player in Topaz Video AI. Split and Side-By-Side previews are now accurately synced, playback will now feel smoother, and over 30 other preview- and playback-related issues have been resolved.

CleanShot 2023-04-18 at 10.51.17

Improving the in-app preview experience was one of our major priorities for the last few months, and it has been quite a major undertaking so far. We’ve tried a few different approaches and built multiple prototypes to make it happen, so we’re excited to ship the first set of improvements to you. Next, we’ll explore building a more efficient video reader to speed up video playback and seeking.

Other improvements

We’ve also made a significant number of other improvements and fixes in the last month:

  • Better update experience
    • Improved in-app update workflow, particularly for paid upgrades
    • Fixed occasional watermark issues when the user is logged in
    • [Win] Added support for patch updates that are around 85% smaller
  • Improved export flow
    • Added ProRes 422 Standard encoder option
    • Added max output resolution of 32k by 32k for image sequences
    • Changed default transcode audio bitrate to 320kbps
  • Improved quality of life for presets
    • Added note when parameters have been changed from an applied custom preset
    • Presets can now optionally save Export settings
    • Switching presets now cause locked filters to disable properly
  • Added proxy support for model downloads in Preferences
  • Preferences → Max Processes limit is now based on detected user hardware
  • Source video panel is now horizontally resizable
  • Parameter values are now retained when switching scales
  • Output list now remembers asc/desc sorting and view filters between sessions
  • Fixed processing failures caused by insufficient VRAM
  • Fixed processing issues on Intel A770 using the latest beta driver (and next official drivers)
  • Fixed some processing failures on Intel Mac
  • Fixed some app window issues with appearance and scaling
  • Fixed Add Noise adding more noise than intended in first few frames
  • Fixed Stabilization issue for very long videos
  • Fixed slow app load when external drives are connected
  • Fixed many UI inconsistencies and other smaller bugs

You can read the full list of changes in the weekly release threads: v3.2.2, v3.2.1, v3.2, v3.1.11, and v3.1.10.

Roadmap Update

While we’re making good progress on our priorities, we’re still focusing heavily on:

  1. A new quality enhancement model that gives more natural results with faces.
  2. Further improving the in-app preview experience with faster playback and seeking.

We previously included performance as a major blocking priority, but with this latest round of optimizations we’re now comfortable elevating other features to the roadmap:

  • Add option to pause and resume* exports and preview processing.
  • Add scene change detection* to improve Stabilization and Frame Interpolation results for videos with multiple scenes. We’ll support this only internally at first, but may later expose scene changes in the user interface.
  • Add option to apply a second Enhancement pass after de-interlacing.
  • Add Apollo 4x model for faster processing and better results on <4x frame interpolation.
  • Add optional ability to use older unsupported models in latest versions.
  • Improve Themis (Motion Deblur) quality with object motion.
  • Improve Output Settings interface and audio transcode options.
  • Improve Video Output list interface for comparing multiple previews and parameters.

We love all the feedback that you’ve given us since release, both good and bad. It’s both motivating and fulfilling for us to see just how much you care about the direction of the app, and we’re committed to living up to that trust. Thanks again for using Topaz Video AI!


Could we have the option to apply two enhancement passes for all videos instead of just videos that are de-interlaced?

I know some people will take progressive footage, apply Proteus 1x to it to reduce the noise, then Gaia 2x to increase the resolution and detail. Being able to apply two enhancement passes like this would be a nice feature.

So this feature is useful outside of the specific case of de-interlacing.


I would like to see bug fixes somewhere on that map. There are still a lot of outstanding bugs that go back 6 months or more since the initial 3.x release.

1 Like

Agreed, stacking models would be nice


The lack of pause and resume functions is too fatal a problem. In the case of videos with a long running time, such as movies, it sometimes takes more than a day to process, but in this case, no GPU-intensive tasks can be performed during the program processing time.


Deinterlacing shouldn’t even be a first pass, to be frank. It should simply be a tickable checkbox (with perhaps an extra one for doubled framerate) on your one-and-only 1st pass. (Much like a VapourSynth filter). And with said checkbox ticked, TVAI should then just proceed with your actual enhancements.


Great, I’m glad you are finally tackling this. Please send out a notification to the mailing list once the feature is ready.
My subscription is currently dormant but I will renew it once that’s out.

1 Like

Topaz V AI 3.2.4 and Beta Proteus with no upscaling on a 2160x1440 video is terribly slow compared to other iterations of 3. I’m getting 1.1 FPS while I was getting 3-6 FPS previously.


OS: Mac v12.0605
CPU: Intel(R) 10 Core™ i9-10910 CPU @ 3.60GHz 128 GB
GPU: AMD Radeon Pro 5700 XT 15.984 GB

1 Like

Hi, new here - so if this isn’t the right place for this comment, please direct me. There doesn’t seem to be any kind of export progress bar to help gauge how long exports will take. Is this by design or yet to come?

Please add this to the roadmap. A “in” and “out” button that you can press when trimming a clip, like in the old version. It’s so much easier to scrub to the point in the video that I want, then use left and right arrow keys to find the exact frame, then to to click the “in” or “out” to set the in or out position.

The bar is at the bottom of the screen. It will tell you how much time is left.

Video Roadmap Update (May 2023)


If I recall correctly, the TVAI roadmap for each month gets released roughly two weeks after the Topaz Photo AI roadmap is released for that month.

And the Topaz Photo AI roadmap is release a short while after the first update for Topaz Photo AI is released for that month.

1 Like

Updated: Video Roadmap Update (May 2023)