this post was submitted on 24 Aug 2024
24 points (100.0% liked)

MorphMoe

305 readers
83 users here now

Anthropomorphized everyday objects etc. If it exists, someone has turned it into an anime-girl-or-guy.

  1. Posts must feature "morphmoe". Meaning non-sentient things turned into people.
  2. No nudity. Lewd art is fine, but mark it NSFW.
  3. If posting a more suggestive piece, or one with simply a lot of skin, consider still marking it NSFW.
  4. Include a link to the artist in post body, if you can.
  5. AI Generated content is not allowed.
  6. Positivity only. No shitting on the art, the artists, or the fans of the art/artist.
  7. Finally, all rules of the parent instance still apply, of course.

SauceNao can be used to effectively reverse search the creator of a piece, if you do not know it.

You may also leave the post body blanks or mention @[email protected], in which case the bot will attempt to find and provide the source in a comment.

Find other anime communities which may interest you: Here

Other "moe" communities:

founded 7 months ago
MODERATORS
24
submitted 2 months ago* (last edited 2 months ago) by [email protected] to c/[email protected]
 

Artist: Onion-Oni aka TenTh from Random-tan Studio
Original post: #Humanization 6 on Tapas

Upscaled by waifu2x (model: upconv_7_anime_style_art_rgb). Original
Unlike photos, upscaling digital art with a well-trained algorithm will likely have little to no undesirable effect. Why? Well, the drawing originated as a series of brush strokes, fill areas, gradients etc. which could be represented in a vector format but are instead rendered on a pixel canvas. As long as no feature is smaller than 2 pixels, the Nyquist-Shannon sampling theorem effectively says that the original vector image can therefore be reconstructed losslessly. (This is not a fully accurate explanation, in practice algorithms need more pixels to make a good guess, especially if compression artifacts are present.) Suppose I gave you a low-res image of the flag of South Korea ๐Ÿ‡ฐ๐Ÿ‡ท and asked you to manually upscale it for printing. Knowing that the flag has no small features so there is no need to guess for detail (this assumption does not hold for photos), you could redraw it with vector shapes that use the same colors and recreate every stroke and arc in the image, and then render them at an arbitrarily high resolution. AI upscalers trained on drawings somewhat imitate this process - not adding detail, just trying to represent the original with more pixels so that it loooks sharp on an HD screen. However, the original images are so low-res that artifacts are basically inevitable, which is why a link to the original is provided.

no comments (yet)
sorted by: hot top controversial new old
there doesn't seem to be anything here