Livestream
in
Workshop: Workshop on Machine Learning for Creativity and Design
Paper Spotlight: Personalizing Text-to-Image Generation via Aesthetic Gradients
Victor Gallego
Abstract:
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 https://github.com/vicgalle/stable-diffusion-aesthetic-gradients
Chat is not available.