“… transition from analog to digital …” that can explain the bad quality of input, but that is why I try to recover it by an AI product.
I agree that output quality should be the first priority. The fact that the “Quality mismatch between 2.6.4. and 3.0.x for some models” (which has existed for a long time in the betas) is still an issue in this version is not a good sign regarding Topaz’s priorities, in my opinion. I realize that Topaz needed to develop a new Video AI, and I think Photo AI was inevitable (I even speculated on such a combination app before PAI’s official announcement), but for much of the past year it really seems like the upscaling AI models have been placed on the back burner.
The face recognition in Gigapixel and Photo AI is excellent for small faces but does not work well for large faces (and in fact the official recommendation is to turn it off for large faces). Since the same face can be of different sizes in different parts of a video, that would mean Topaz needs one of two modifications:
- Modify the face recognition feature to work on faces of arbitrary size. This option is probably not a good idea since the usual upscaling models work well for large faces.
- Activate the face recognition feature for faces that are smaller than a certain threshold. To avoid sharp transitions as the size of a face changes, for faces slightly larger than the threshold it could upscale the face with and without the face recognition, and then blend the two.
1 Like
the artemies modes lost a lot of their early abilities of recovering details by the attempts to make them look “more natural”. that’s sad. fortunately the early artemies modes are still included in the de-halo modes, so adding a bit of de-halo brings back details. but it also gives the image a dreamy look. the “recover details” option in opposite does not recover details but makes the existing ones more visible. 
3 Likes
For me – VEAI 2.6.4 seems to be the best option available. I can stabilize video in FCPX or AE (so I don’t care about the feature). I can de-interlace with Compressor (so I don’t need this software to do it). This software filled a void of video enhancement that you could not find anywhere else.
No sense in re-inventing the wheel on some features. I hope the software stays more focused, with fewer features – but features that do an excellent job.
For what I do it takes .09 seconds per frame and the results are very nice – using Mac Mini M1 16GB.
I hope Topaz will continue to support v2.6.4 (not expecting any changes) – just for it to continue to function. That is my worry.
When Version 3 is better in performance than 2.6.4 – then I will be glad to upgrade.
Regarding face recognition in video – that is going to be tough to offer at a speed that is acceptable. I don’t see that option being available in the near future. I’d rather just have fuzzy video on faces.
Now - these forums are awful to navigate. They aren’t support forums – they are bug forums.
I hope at least these can be cleaned up. Beta testers should have their own private forum.
4 Likes
There is no beta version of Version 3 now that it is a released product. That is why you see beta testers replying to this forum. They are labelled as beta testers here because they are registered as beta testers of any beta version. When version 3 was still in beta stage the beta testers did have their own forum for each beta release.
1 Like
We’re aware of the performance regression and it’s one of our top priorities to address. As for the license expiration, if your license covers v3.0.0, you’ll be eligible for any v3.0.x version.
7 Likes
Hi, I’m brand new to this and only just started to use v. 3.0.2 yesterday, with varying success. ‘Processing Failed’ in Preview being a disappointment with one video.
How do I download 2.6.4 which most seem to prefer?
Thanks.
Mac
https://downloads.topazlabs.com/deploy/TopazVideoEnhanceAI/2.6.4/TopazVideoEnhanceAI-2.6.4-univ.dmg
2 Likes
What’s going on here?
Topaz sells this product for hard cash and we get a lot of bugs and many ‘retries’, bugs, instability etc…
WHY sell a product that is not even did a beta testing, because reading all comments here, this seems to be the case.
It’s slower than 2.6.4., more difficult to use, and really FULL of bugs!
WHEN is this product mature enough to be used by the users who pay for it?
4 Likes
True, we should change the title to ‘Not ready for primetime software tester’. 
I’d give it a few more months, at least. Actually, it did have months of alpha and beta testing, but here we are.
Thanks for this my friend!
1 Like
Hi again, I’ve downloaded it but in the top left corner of the UI it has a ‘BUY’ logo. As I’ve paid for the latest version should the 2.6.4 version show as already purchased or do I have to register again. I sound such a newbie because I am 
just log in with your login data directly in the application. its in the pull down menus on the top.
2 Likes
Thanks again… sorted!
1 Like
Is this released product being sold to customers not knowing it functions properly?
For the sanity of new people, sell 2.6.4 and label version 3 as an experimental version.
Version 3 could hurt the reputation of this company. It doesn’t make sense to advertise a product that is not worthy of being sold yet.
It appears to me that there is another issue behind all of this as it does not make sense when 2.6.4 was for the most part, fully functional.
This we will never know.
5 Likes
Many people say that the problem will come from the change of the VEAI team that it all went to shambles. It’s not me who says it, but quite a few people on this forum. After me I didn’t know the old team, so I can’t judge if the old VEAI team was better than the current one. But personally, yes 2.6.4 will always be the best version for now.
4 Likes
What I meant was the transition from analog to digital broadcasting also caused the encoding standards to evolve again.
Is there any way to download all of the AI models at once? I have slow rural internet service (7.7Mbps on a good day) and if I could just download the models at a convenient time, rather than waiting when I need to start processing a video, it would be very helpful to my productivity. I started to process a video nearly 10 minutes ago, and I’m still waiting for the AI model download to complete, can’t do a thing yet.
3 Likes
Anyone got their license extended after the beta testing? Kinda feel like I wasted my time on testing the 3.0 betas.
2 Likes
