Schr\"{o}dinger's Bat: Diffusion Models Sometimes Generate Polysemous Words in Superposition. (arXiv:2211.13095v1 [cs.CL])

Recent work has shown that despite their impressive capabilities,
text-to-image diffusion models such as DALL-E 2 (Ramesh et al., 2022) can
display strange behaviours when a prompt contains a word with multiple possible
meanings, often generating images containing both senses of the word (Rassin et
al., 2022). In this work we seek to put forward a possible explanation of this
phenomenon. Using the similar Stable Diffusion model (Rombach et al., 2022), we
first show that when given an input that …

arxiv diffusion diffusion models superposition words