A study shows that AI image generators often default to 12 specific photo styles, regardless of the initial prompts. When tested through a visual telephone method, the images quickly lost detail but consistently converged on these familiar motifs, described as "visual elevator music."

GigaTok is a novel method designed for scaling visual tokenizers to 3 billion parameters, addressing the reconstruction vs. generation dilemma through semantic regularization. It offers a comprehensive framework for training and evaluating tokenizers, alongside various model configurations and instructions for setup and usage. The project is a collaboration involving extensive research and experimentation, with resources available for further exploration.