Information Theoretic Text-to-Image Alignment

Diffusion models for Text-to-Image (T2I) conditional generation have recently achievedtremendous success. Yet, aligning these models with user’s intentions still involves alaborious trial-and-error process, and this challenging alignment problem has attractedconsiderable attention from the research community. In this work, instead of relying onfine-grained linguistic analyses of prompts, human annotation, or auxiliary vision-languagemodels, we use Mutual Information (MI) to guide model alignment. In brief, our methoduses self-supervised fine-tuning and relies on a point-wise MI estimation between promptsand images to create a synthetic fine-tuning set for improving model alignment. Ouranalysis indicates that our method is superior to the state-of-the-art, yet it only requiresthe pre-trained denoising network of the T2I model itself to estimate MI, and a simplefine-tuning strategy that improves alignment while maintaining image quality. Code available at https://github.com/Chao0511/mitune.