Personalized Image Generation via Human-in-the-loop Bayesian Optimization

Imagine Alice has a specific image x^ast in her mind, say, the view of the street in which she grew up during her childhood. To generate that exact image, she guides a generative model with multiple rounds of prompting and arrives at an image xp*. Although xp* is reasonably close to x^ast, Alice finds it difficult to close that gap using language prompts. This paper aims to narrow this gap by observing that even after language has reached its limits, humans can still tell when a new image x^+ is closer to x^ast than xp*. Leveraging this observation, we develop MultiBO (Multi-Choice Preferential Bayesian Optimization) that carefully generates K new images as a function of xp*, gets preferential feedback from the user, uses the feedback to guide the diffusion model, and ultimately generates a new set of K images. We show that within B rounds of user feedback, it is possible to arrive much closer to x^ast, even though the generative model has no information about x^ast. Qualitative scores from 30 users, combined with quantitative metrics compared across 5 baselines, show promising results, suggesting that multi-choice feedback from humans can be effectively harnessed for personalized image generation.