First off my subscription is currently on hold and I’m still using 2.6.4 partly because the long promised pause/resume functionality is not implemented yet and mainly because it’s just much more useable.
The preview is real time for every frame vs the temporary video
There’s no forced menu diving when selecting models if you don’t want that.
The 4 way split preview is great to quickly compare and judge which model works best but completely missing in the new UI.
There is no hidden menus (hamburger menu) which are just unnecessary.
Is anyone feeling the same? Are you a 2.6 holdout?
Can you provide us an explanation of why the old UI was scrapped instead of extended with new features? Is there a chance that new models be backported to the old UI?
First of all, you never need to purchase an upgrade license unless you feel that an update necessitates the price tag.
Pause and resume is on the slate for this quarter and I would recommend keeping tabs on the roadmap posts.
v3.x creates temporary files to allow you to preview as many models as you wish to. v2.6.4 while appealing for the 4-way view is quite limiting when you want to preview more than one video at a time or wish to process a view while previewing another. There are massive limitations with v2.6.4.
“There’s no forced menu diving when selecting models if you don’t want that.” I am unsure what this means, can you explain? Also; “There are no hidden menus (hamburger menu) which are just unnecessary.”
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.