... unique images that don't exist, such as "the Eiffel tower is landing on the moon," by combining multiple concepts together. Optimizer updated to Distributed Shampoo, which proved to be more efficient following comparison of different optimizers. New architecture based on NormFormer and GLU variants following comparison of transformer variants, including DeepNet, Swin v2, NormFormer, Sandwich-LN, RMSNorm with GeLU/Swish/SmeLU.