Uploaded by michielbos 
512x512 PNG 353 kB
Interested in advertising on Derpibooru? Click here for information!
Help fund the $15 daily operational cost of Derpibooru - support us financially!
Description
This picture is the result of a neural network attempting to reconstruct a picture of a Chinese bootleg Celestia plushie.
The neural network is in progress of learning to reconstruct frames of MLP episodes from smoothed 32x32 pixel images to 512x512 pixel ones. Since the network had no experience with either photos or unsmoothed images, inserting an unsmoothed photo of the plushie created this beautiful piece of art.
The neural network is in progress of learning to reconstruct frames of MLP episodes from smoothed 32x32 pixel images to 512x512 pixel ones. Since the network had no experience with either photos or unsmoothed images, inserting an unsmoothed photo of the plushie created this beautiful piece of art.
Source
not provided yet
awesome, thanks. that looks amazing
I made a comparison video to demonstrate what it does when it is given a part of an episode.
https://youtu.be/_qtzGFYV–Q
Edited because: fixed link
Squints
My eyes aren’t working…