zlacker

[return to "RealFill: Image completion using diffusion models"]
1. Jorge1+3a[view] [source] 2023-09-29 19:16:03
>>flavor+(OP)
Wow. The use case that comes to mind for me is when you take a big family photo (or 20) and someone inevitably ends up cut-off by accident.

So then you just feed RealFill the 20 pictures you took and your uncle is magically painted in.

◧◩
2. jetrin+Fa[view] [source] 2023-09-29 19:20:32
>>Jorge1+3a
Also getting everyone smiling with their eyes open at the same time. Phone cameras could record a group photo for five or ten seconds and use the best expression from different times for each person.
◧◩◪
3. twism+Kb[view] [source] 2023-09-29 19:26:58
>>jetrin+Fa
From the leaks this may be coming to the Pixel 8
◧◩◪◨
4. ChrisC+qD[view] [source] 2023-09-29 22:15:06
>>twism+Kb
Leaks? Wasn't this a launch feature in Google Photos, while it was still Google+ Photos?

It was supposed to adjust eyes to open them if you took multiple photos.

◧◩◪◨⬒
5. twism+FL[view] [source] 2023-09-29 23:19:01
>>ChrisC+qD
That's "Top Shot" which is the entire frame. The feature I'm referring to would adjust multiple faces in a frame by selecting the same faces/sections from different frames to a single target frame
◧◩◪◨⬒⬓
6. ChrisC+uR[view] [source] 2023-09-30 00:08:46
>>twism+FL
I swear that's what was announced, but I assume you're right because you actually know the term Top Shot, and I had no memory of that.

So your memory is probably better than mine. :)

I just remember some demo of a family shot and it automatically opening a little boys eyes by using another photo. And another auto combining of images so that you could take a lot of photos of a busy tourist place and automatically remove all the people.

[go to top]