Posts

I can tag some pictures as ‘luciferamon eye style’, ‘lumineko head shape’ and ‘ears from imalou’.

I can believe this if Rainbow Dash was not in the training set. But it is actually is in the training set. And we can perform an experiment — if we remove Rainbow Dash form training set, I am 100% sure Rainbow Dashes will disappear from output.

I can write my mirroring script as unreadable “Brainfuck” language complied to assembly to make it harder to proove that it uses existing character to produce the same character. Or I can just hide sources from you. Still you will believe more your eyes and don’t try to spend your time to proove that this script get mirrored images in not-random way. You will just ban mirrored reuploads without any proofs.

“rainbow dash with horn” or “wrong eye color” or “alternative hair style”

I’m about to change my mind…

https://thisponydoesnotexist.net/v1/w2x-redo/jpgs/seed62816.jpg

This is very philosophical question, why random generator in artist mind is something different from random generator inside the generator

Also, it is was AI generator developer intention, to take existing characters into training set.

• should this be tagged as Rainbow Dash? Canon character does not have a horn — https://thisponydoesnotexist.net/v1/w2x-redo/jpgs/seed91950.jpg  
• should this be tagged as Pinkie Pie? Canon character does not have a white line in mane and horn — https://thisponydoesnotexist.net/v1/w2x-redo/jpgs/seed62816.jpg  
• should this be tagged as Rarity? There are dozens of OCs with more similar design — https://thisponydoesnotexist.net/v1/w2x-redo/jpgs/seed64832.jpg
   
  Difference with your case is that you intentionally fed only Fluttershy pics. Result of uncontrollable mix of multiple character is really pain to moderate.
   
  Oh, and wait until some artists will recognize their style and ask to tag them.

• The ponies might actually already exist, but these specific images of them do not.

Do not tag these with canon character tags no matter how they look.

Ce n’est pas un Rainbow Dash

1. Something is using existing pictures of the character to produce the character. Something is “Artificial Intelligence” or SFM screenshot or human with pen and paper or human with some advanced tools like Photoshop or human with command line tools or “Artificial Stupidity” or mix of all this. Doesn’t matter.
    
2. Output looks like this character.
    
   Why any reason to not tag as this character?
    
   Sometimes there are slight deviations like other eye color, they can be tagged too. There are some “grey zone” for some outputs when there are too much deviations, but why remove tags when the ouput have exactly all features of the character without any ambiguity?

1. just tag [character]  
2. [character], wrong eye color  
3. [character], multiple horns  
4. maybe [character1], [character2], fusion…?

Have a look at this search. Today, 2020-07-17, you’ll see it contains a lot of images that should be tagged fluttershy, twilight sparkle, etc. but aren’t. I’ve tried tagging them, but it turns out that not everybody agrees on whether these images should receive the character tags.

This is due to thisponydoesnotexist being an AI (a generative adversarial network to be specific), and to the name of the site: “This Pony Does Not Exist”… if the pony does not exist, it cannot be a know character, and must be a new OC each time…

So here are two questions:

• (A) Should we tag the images: according to “what they look like” (A1) or according to “what they were meant to be represent” for the author (A2)

Note that in the case of (A2) we still need to decide if the person selecting the image in the pool generated by the AI has the value of an author, in the absence of any other author (yes (A2.1)) (no (A2.2)). Please also note that there are thisponydoesnotexist images tagged “not fluttershy” by the uploader, so the difference between (A1) and (A2.1) matters.

• (B) (from a more practical viewpoint) What should we do about the tagging conflict of the thisponydoesnotexist images?