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. xwdv+qd[view] [source] 2023-09-29 19:36:50
>>Jorge1+3a
You don’t even need to take the photo, with enough images of each family member and images of a tourist destination you can just automatically construct a photo of everyone together at the location, saving the costs and carbon footprint of getting everyone together.
◧◩◪
3. cubefo+Kh[view] [source] 2023-09-29 19:59:13
>>xwdv+qd
And then why demand "photos" of family excursions at all, when it is just an AI imagining how things probably were happening at the time, or would have happened? We should just stick to our own imperfect memory.
◧◩◪◨
4. therei+aX[view] [source] 2023-09-30 01:11:29
>>cubefo+Kh
I'd imagine in the future we could have services such as this one:

> In exchange of a small fee and a 35 minutes suggestion session, get you and your family implanted with memories of a beautiful vacation that'll last you for a lifetime for fraction of the cost of an actual one.

[go to top]