If you can notice it - Yes!
Absolutely no correlation whatsoever.
Hmm, I’m surprised. The person that said it is quite knowledgeable about such things and highly regarded.
In your samples, you are sure everything else was equal? The one on the right looks crisper, but I’m not sure if that’s because it is oversharpened.
Of course, but mind you that was one of the few occasions were the difference was that drastic - For the most part there was virtually no difference between the two, expect that maybe fp32 was better at rounding errors, but at the end there’s nothing to boast about really.
I just thought to myself that even if fp32 usually produces identical results to fp16 it can sometimes just “pop-off” out of the blue, and with no speed penalty (using an amper gpu) to justify staying with fp16 , forcing veai to use the fp32 models as default seems like a no-brainer to me.
What about those pesky compression artifacts, with large patches of boxes that ruin the image? What filter will you use in that case? I will upload an example soon.
I’ve made a test with GAIA-HQ forcing fp32 on a RTX 3090, not only it is 2 times slower but also there is absolutely no eye visible difference even at 400% zoom vs fp16. Just a very very tiny difference only visible on a vectorscope.
Maybe was just the test video I pick but why would it be 2 times slower when for you there is no speed difference ? Or was it for Artemis ?
Hi guys. Check this method out. I just discover it. No artifacts and detail smoothout with all models.
Can you post screenshots because I had trouble replicating your claims. The only way I could get “ERR” to show up on the lower left was if I set the default to SD, HD, or 4K. After importing a video go to “sizing” and choose “Custom setting”. Now “ERR” will appear behind whichever model you choose…but it doesn’t look any better. In fact it looks exactly the same. If you try changing the Scale % to 200 or whatever the “ERR” disappears and the program behaves normally.
It makes a lot of differences. If you upscale low resolution footages, you will see what I’m talking about. I had to upscale a 25m video for 10 days and I know where the artifacts appears. But after doing this, no artifacts appeared. I saw 4K UHD + 200%/450% and ERR. And indeed ERR has less artifacts and most details are preserved. Only 4K/8K UHD, Full HD, SD presets give artifacts.
It would be really useful if you could post a screen shot of the interface when ‘err’ shows up. Also a comparison of the same frame with and without artifacts, as you claim. Personally, I use custom sizing a lot of the time and have never noticed this. As well, it occurred to me that if ‘err’ (indicating error) does show up for whatever reason, it could mean that it is only a normal upscale without AI enhancement.
Why? The clip with typical problems from my old Canon G9 - flickering, artefacts, dancing pixels even in daylight. And the clips shows the scenery with potentially plenty of details and some architecture. I have analysed and it seems the file you have uploaded does not contain details, plenty of them had been removed. Of course thank you for help, it is important contribution to my workflow.
Below my attempt as described earlier:
https://we.tl/t-QnJCgHeyGq
So far this method gives me the best results - I have not sharpen the footage so probably some sharpening could also be beneficial.
But I have used similar approach, I have just choosen 225% to upscale my 640x480p clips to 1080p. What is the difference?
Full HD option and Custom setting option make major difference about artifacts. Almost no artifacts or detail smoothout like I used to have with Artemis.
It’s really hard to compare because the pictures will be compressed when I upload them here.
I tried everything, and I can’t get the ‘err’ to show up. Tried on both versions, 2.2.0 and 2.1.1. When I enter any percentage in custom size, it shows up beside the model. Eg. Artemis HQ v12 150%. Also, there is no ERR where the size presets are listed. That’s why I wanted to see what your interface looks like.
I can’t replicate this ERR. It never appears in my case. It seems it’s a bug that only affects certain installations.
Thanks, I’ll try your settings and see what happens.
EDIT: Nope, no ERR. It displays the 450% instead, or any percentage I fill in.
You mean blocking artifacts? An example will definitely help identify the issue.
Yeah, all the tests I did were with the artemis models and I haven’t noticed no speed reduction using those so… I just assumed it would be the same for gaia too but I guess I was off the mark on that one lol.
Thank you for helping me test those though, I shall keep them on default fp16.
Please do not make duplicate posts - once is enough.
But I used Custom version, you know it, 225% from 480p to 1080p and there have always been some problems.
Could you upscale me this ProRes file by your new method to obtain both 1080p and 2160p? I am very curious if it is really good. Please prepare ProRes file.
https://we.tl/t-nYQM8UPqPn
By the way, could you also write your performance (frames/ sec of such method)? You have very the fast workstation.
Thank you.
PS My attempt is above (Bridge) but I finally saved as mp4 but all intermediate step were ProRes and DNxHR.
