Generated images from text prompts with VQGAN and CLIP (z+quantize method).

AI generator credits:
Originally made by Katherine Crowson (https://github.com/crowsonkb, https://twitter.com/RiversHaveWings). The original BigGAN+CLIP method was by https://twitter.com/advadnoun. Added some explanations and modifications by Eleiber#8347, pooling trick by Crimeacs#8222 (https://twitter.com/EarthML1) and the GUI was made with the help of Abulafia#3734.


The key word that the AI was generating an image using was "Minecraft Skin". It looked through a large sample size of what comes up with this query, and tries to make it's own image that would fit the category.