We’re preparing to launch the first Beta of Video AI 6 next week!
We made a video just for y’all, so you can see some of the highlights in action.
We wouldn’t be here without our community! That’s why we’re sharing the upgrades coming your way here first.
Highlights
Tabs
We’ve heard your feedback and we want to make comparison, easier, better, and more intuitive. Tabs are self contained groups of settings. You can create them from scratch or use presets. They replace for our previous preview queue and A/B comparison mode. Now rendered previews are contained in each tab, and it’s easy to compare two sets of previews, or the original. Just drag the tabs to create the view you want.
Video player
Our upgraded video player has been available in Windows and is now coming to Mac. The video player supports HDR, audio, and smooth 8K playback. Getting high quality previews in app, has never been better. Note: HDR support on Mac is still in progress
Exports
We’ve revised the export queue to take up less space, offer more information about your exports, and make it easier to track exactly what you’re rendering.
Sources
We’ve moved the sources panel to create more work area. You’ll find it right below the timeline on the right.
Presets
The preset system has been refreshed to make it easier to find your favorite settings and quickly apply them across projects. You can select a preset directly when starting a new project. Presets are tightly integrated with tabs, you can create a tab from a preset, or save a tab to a preset.
Timeline
We gave the timeline a lot of love in this update. The upgraded timeline is faster, more responsive and has thumbnails to help you find what you’re looking for.
Live render
We’re making huge improvements to the live render system. You can render specific length chunks using the render button, and now it’s easier than ever to compare two sets of settings. Just switch into Side by Side or Split View, and press the play button to start rendering.
Beta next week!
We are spending more time working on these features and testing them with users. We hope the effort shows. We are planning to make lots of improvements through the Beta period, and we want your feedback to make this feel like a huge upgrade with a smooth transition.
While I appreciate the various changes outlined in the video, I am still really hoping for an Adobe Premiere plugin. I often have long-form multi camera edits where just one of the cameras needs enhancement, but I don’t want to have to render the entire footage from that camera; just the short portions I am using.
So it seems it is mainly focused on UI/UX this new version.
Any new AI modules along with it (v6) or changes to existing AIs (e.g. Reah/RXL x2 support, etc.)?
Thanks for the preview. Personally I’m still hoping for an improvement in picture quality enhancement for my old vhs videos and better stabilization for super 8 films. Thus far I still get either a plastic look or strange artifacts like extra eyes or teeth.
The stabilizer tends to be a hit and mostly miss for older shaky videos.
Nevertheless I’m sure this will eventually also improve as time goes on. Perhaps there aren’t enough Topaz users out there to make this a priority.
If we could integrate with Premiere, we would. There are limitations with how Premiere specifically handles compute that makes an integration extremely difficult / impossible. Other apps like After Effects and DaVinci Resolve handle compute in ways that make integrations / plugins possible.
Looks good. I hope that big, long grid space will be used for something better. And mostly I’m interested in the best quality exports.
Thanks very much.
mp
Corresponding to some feedback about possible plugins for PremierePro I wonder if we have an API access to the engine yet, so that I could begin implementing a plugin to other applications?
I think its not necessary to extend Video AI to re-invent the wheel in every aspect, but to give us the most advanced AI tools to enhance video.
I also hope Topaz is looking not only into upscaling, denoising but also repairing artefacts, restore old images & film, potentially colorizing it too at some point.
Would they be Topaz if they didn’t change the UI every major version?
Anyway, this will be interesting to test out, but nothing I need looks like it’s going to be added with this version.
I’m really hoping for the duplicate frames replacement/interpolation functionality is fixed in that release… And the TEMP wipe bug - this one is DANGEROUS.
Did you perchance also listen to folks like me, who are dying for a way to ‘preview’ (postview, maybe?) already processed sections in the timelines, to see what the result was there? Vital, so you can abort early-on when, say, a distant face got mangled along the way.
EDIT: ‘postview’ was already present in v2.6.4, btw.
While I appreciate these new improvements I´d expected some improvements on the AI models with this new major version as well. So thumbs up for the UI/ UX, but sigh for model improvements…
I hope we don’t get more bugs we already have, and existing ones will be fixed. Things like variable frame rate that can happen, blanc screens on previews and other bugs users reported. A stable version would be much more important to me than new features and visual UI improvements.
And then I think the main focus should be on optimizing the models.
The lgoal should be having less but to perfection trained models, It doesn’t help us if we have a dozen models and each one has somewhere strong weaknesses. In addition, it is difficult for Topaz to bring so many models to a higher level, so less but better ones I think is the way to go.
you can decompose multicam in a copy of a timeline, export only that cuts, and replace them. it’s tediuos i know, but better and faster then render all camera footage for few seconds.
!
