I imagine Recover Beta v2 and a Gigapixel Beta version. Is that right?
In your test photo, I prefer the final result with creativity at 2. It preserves details better. On the others, they’ve changed a bit.
Visually they seem identical. I could rerun a test and subtract the outputs to see if there’s any visible difference.
I assume v8.3 will be out soon.
In many respects I prefer Creativity 1. Look at what I think are cutout figures of people in traditional Chinese dress. This is at 200%:
Creativity 1
Creativity 2
Creativity 3 turns them into elephants!
Mostly, given that it’s faster, I am using Creativity 1 on these old photos. Every so often, elements like grass or gravel in the foreground are rendered poorly, and I find I can improve them using Creativity 2 along with some text prompts.
This is correct. The Creativity 1 and 2 settings are much different than 3 and up, running a different architecture under the hood.
Thanks. That’s very interesting. I guess we all need to experiment to find the settings that we like best for our particular needs. It’s just a pity that it’s all so slow on my Mac mini M4!
1 Like
Ah, that’s why the results are so different on the border between 2 and 3. I had a vague impression that it was done in a different way, because the difference is really dramatic. 2 is most often suitable for me, but sometimes only 1 is needed.
I always have to experiment, I’m not very good at estimating the correct parameter values (and especially their combinations). It probably works better for series of very similar photo contents. Fortunately, I only play with a maximum of a few dozen photos for my own pleasure, so it’s survivable. I use a laptop with Windows 11 (Nvidia Geforce RTX 4070 laptop GPU, 8 GB), so it works quite quickly for me (mostly in the order of minutes, sometimes to lower tens of minutes (say 15-40), usually much less than 60 minutes).
1 Like
Thanks for the tip and example, I’ll try it. I should probably write longer prompts, I usually write 1 or 2 not-so-long sentences; that’s probably not enough.
1 Like
It seems to me that for each Creativity value the result has a lot of changes compared to the first image.
It might be worth trying TP Photo AI with the Super Focus Beta tool to see if that gives a better result. For me, the Super Focus sometimes helps (but other times it doesn’t at all).
1 Like
I see. But ideally, you want to combine the best parts of each variant to get the perfect photo.
1 Like
Yeah, with AI tools these days, it’s handy for recreating an accurate description of an image.
1 Like
Indeed, that’s what I have done on a number of occasions.
1 Like
Will there be a GAI update tonight?
Hello - no, it’s not tonight
Will the redefine fix on Mac Silicon be in the next release?
1 Like
It’s crazy how long it takes to process generative recover without even upscaling the image. It’s unusable.
Keep an eye out for Recovery v2 coming soon!
3 Likes
But when is Recovery2 also available for Intel iMacs with AMD GPUs? Any News here?
According to my experience (comparing a Mac Studio M2Ultra with a windows PC with NVIDIA 4070 and another with 4060): yes, no real difference.
Of course, those generative models cannot be fully exactly compared as they deliver a bit different results in different runs even on the same machine due to the nature of the underlying technique.
