Personalizing Text-to-Image Generation via Aesthetic Gradients

Aesthetic gradients guide a CLIP-conditioned diffusion model to generate images aligned with user-defined aesthetics using qualitative and quantitative experiments.

Open

Year: 2022
Venue: arXiv 2022
ArXiv: arxiv.org/abs/2209.12330
URL: arxiv.org/abs/2209.12330
Authors: 1
Hosting: Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text: arxiv.org/abs/2209.12330ARXIV-DEFAULT
TL;DR: Semantic Scholar

Attribution policy →

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

Authors

Víctor Gallego