Personalizing Text-to-Image Generation via Aesthetic Gradients

09/25/2022
by   Víctor Gallego, et al.
0

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

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset