Mona Lisa is drinking Wine with da Vinci.

All about my Creativity Check prompt. And my thing with la Gioconda

Remember your first time? That complicated and almost transcendent moment when you typed a prompt into a txt2img model to see what would happen next?

For me, it was this one:

Mona Lisa is drinking wine with da Vinci.

Why? Diffusion models mostly work — briefy explained — with diffusional (noise=>realism) visualizization of “priors” (“Platonic ideas”-alike concepts). Prior can also be understood also as coherence of text and image in semantic way, in pre-visualized state of being.

The Mona Lisa as one of the most iconic images was also mentioned by Walter Benjamin in his essay “The Work of Art in the Age of Mechanical Reproduction” (1935, PDF). In his text, he wrote about the de-auratization of art. In the past, you went to a museum, admired a work of art, and felt its “aura,” its “uniqueness” (“unique appearance of a distance, however near it may be,” W.B.). With technical reproduction, you could hang a picture of Mona Lisa anywhere, in your room, see it as a print on a bag, and the aura would disappear.

I believe, that AI brings back the aura to the artwork, especially when it is metamorphed via AI into…