Topaz Video AI 4.0?

Yesterday after watching a cat video that someone sent me, I scrolled through an ad for “pre-ordering” Topaz Video AI 4.0 for $249 for 12 months plus a three-month extension. I haven’t heard a peep about an imminent 4.0 release on October 18th, so this struck me as odd. Was that a legitimate ad or a scam?


Video AI 4 is definitely real! :slight_smile:

Coming October 17th, free for users within their upgrade license period.


This is intense! border line magic :sunglasses: (if it can be better than v3)

How did I miss this? Even doing a web search for “Topaz Video AI 4” didn’t turn up a single hit. How is 4.0 different from the current version? I’m excited to hear more!

We’re rolling out a full campaign that will detail the changes in Video AI 4 in the next few days. I’ll update this thread with links when ready!


I was also surprised! I just saw the email right now.

1 Like

I get that Video AI 4 is Ultra, but what exactly is new.

Also I hate the timing. I wish I had a crystal ball and knew what the Black Friday was going to be. I’m definitely buying the upgrade, but do I do it now or wait a month? :weary:


I got that email, its legit and I’m very excited .


Hope you guys address all the major issues found in 3.4/3.5


Stabilizer is very useful on my 15 yr old clips. I hope Topaz can apply that with no zoom at all in v 4.

If we pre-order 4.0, do we get access to the current version until the 17th or do we just have to wait to use the software at all?

The v4 pre-order will only open access to the app on the 17th, with an additional 3 months of upgrade license time added to the usual year-long period.

Ordering the app today for the regular price will also grant access to v4 when it is launched, but will not include the additional upgrade time or the discounted price.


When will be the last date to pre -order. ?

Also If I pre order it now will i be able to use the previous version right away ?


Topaz is spitting out versions faster than some companies have in their entire insistence. I don’t mind that, but they need to fix issues from previous versions first and look at community requested features or add features that are standard in most programs these days, like shut down pc after a job is done, bringing back auto save, etc…


Keen to know what’s new in 4.0, seems quite quick after 3.5 which had some nice improvements.

Any news on a Premiere plugin? That would be the next gamechanger

1 Like

Any updates on that feature change campaign rollout?

  1. With Video AI 4, improve your workflow with new Direct Comparison UI: side-by-side, slide-over, and overlay views to compare your footage using 24 AI models. Built for creative pros who want more fine control. Ultra smooth, Ultra sharp, and Ultra steady.
  2. Direct Comparison UI to preview images and compare any two of your 24 AI models directly. Fine tune settings with side-by-side, slide-over, and overlay views to get the perfect video enhancement.
  3. Nyx v2: Improved training on the Nyx model generates better detailed results while eliminating ISO noise and compression artifacts.
  4. Nyx’s new 2x scale mode enhances the sharpness and fidelity of your footage during the de-noise process.
  5. Nyx can intelligently detect and heal some of the visual artifacts created by video compression.
  6. Iris MQ with improved face recovery
  7. 50% speed gain on TensorRT-compatible GPUs
  8. Custom mode for processing black-and-white video
  9. Custom mode for 3:2 pulldown/inverse telecine footage
  10. Options for deinterlacing at single frame rate or double frame rate
  11. Split Iris into Iris LQ/MQ
  12. Reduced loading times for Enhancement models
  13. Support for rotating videos 90, 180, and 270 degrees-corrects videos with missing metadata for rotation.
  14. Use two Enhancement filters at once. This system will allow editors to stack Enhancement filters and process multi-step AI tasks in fewer clicks.
  15. Animated tooltips that instruct new users on the use of the Preview system the first time the app is run.
  16. Improved dynamic bitrate controls: The High setting for H264 and H265 exports has been adjusted to target a VMAF score of about 95, and is now the default setting for new installs of Video AI.
  17. The lossless FFV1 codec is now available by default in the export options panel, and can be used at 4:2:0, 4:2:2, and 4:4:4 chroma subsampling levels.
  18. AV1 encoder for AMD 7000 series GPUs and 700 series integrated graphics.
  19. Copy all subtitle tracks for MKV exports.
  20. New preference to default to searching for image sequences during import.

Any news on if we can now pause rendering?