Skip to yearly menu bar Skip to main content

Workshop: Workshop on Machine Learning for Creativity and Design

Personalizing Text-to-Image Generation via Aesthetic Gradients

Victor Gallego


This work proposes aesthetic gradients, a method to personalize a CLIP-conditioned diffusion model by guiding the generative process towards custom aesthetics defined by the user from a set of images. The approach is validated with qualitative and quantitative experiments, using the recent stable diffusion model and several aesthetically-filtered datasets. Code is released at

Chat is not available.