In this work, we revisit these famous optical illusions with a generative twist. With the help of latent rectified flow models, we propose a method to create anamorphic images that still retain a valid interpretation when viewed directly. Authors Pascal Chang (DisneyResearch|Studios/ETH Joint PhD) Sergio Sancho (DisneyResearch|Studios/ETH Joint PhD) Jingwei Tang (DisneyResearch|Studios) Markus Gross (DisneyResearch|Studios) Vinicius Azevedo (DisneyResearch|Studios) LookingGlass: Generative Anamo...