Okay, modern life doesn't ENTIRELY suck.

God bless the internet.

Is it photoshop or is the raccoon actually in a silly hat?
- Unbelievably, the picture is of the hat, the racoons was shopped in.
- I believe this is Pope Raccacoonie the first if I recall correctly
- This one unfortunately smells like AI.

Hey, when I was a kid in the 90s if you wanted to see a picture of a raccoon you'd spend all day online waiting for it to load! If you knew the right guy at school though you could get a 1/4" floppy disk already loaded with raccoon pictures so you wouldn't have to wait so long...

raccoon
Yeah "raccoon"
- Don't kink shame me.
omg I completely forgot how tiny raccoons were in the 90s.
Oh Captain Janeway. Lace, the final brazier
You mean beaver.
- Big brown beavers
5.25", or 3.5"? We had both at my parents' house in the 90s, but the standard was 3.5"
I think there may even be an external 8" floppy drive in my parents' barn.
- This would have been around 95 or 96 so definitely 3.5" floppies. The same guy said he could get me bootleg copies of Duke Nukem 3D and Rise of the Triad and they both came on huge stacks of 3.5" floppies that he expected me to give back to him lol

In case anyone wants to see this:

That's a fairly normal hat.
- It knows some very entertaining stories once you get to know it better.
Our Lord Raiden.

If you wanted to watch a raccoon try to wash cotton candy, you'd have to find a raccoon and give it some cotton candy.

https://i.imgur.com/Jj4WK1a.gif
Now you can just describe a specific raccoon video and be presented with it by a stranger who also loves this video.

Now we can generate one in a few seconds that has never existed jsuf by touching our phone in the right places a few times

TeChNicAlLy it sort of already existed. A diffusion model can only generate an impossibly huge but finite number of images, and the content of these images is determined when the model is created. So when you 'generate' images you're kinda just browsing a catalog
- That's not correct. It allows permutations of concepts it has "identified". It's only finite in the sense of being limited by the number of pixels and possible color values.
  This is far from what "browsing a catalog" makes it sound like. It's almost correct if you consider the catalogue as a collection of concepts. But it is literally generating an image based on a prompt that projects those concepts to an image. You can generate something with a combination of concepts, mixed together in a way that were never part of any training set
  A racoon with purple fur, wearing sunglasses and a metal viking helmet with ivory horns, the blue planet earth is visible in the starry background
  It doesn't do a perfect job, but I also spent 2 minutes on this.
- Besides the point the other commenter already made, I'd like to add that inference isn't deterministic per model. There are a bunch of sources of inconsistency:
  GPU hardware/software can influence the results of floating point operations
  Different inference implementations can change the order of operations (and matrix operations aren't necessarily commutative)
  Different RNG implementations can change the space of possible seed images

50 years ago? Yes, that's true, but it was true 25 years ago too. For a lot of people it was true as recently as 15-20 years ago.

In the 90's you'd have to watch America's Home Videos, complete with Bob Sagat and commercials to see the same stuff freely available all over the internet now.

you may haz cheezburger

https://lemmy.world/c/raccoons