Personalizing Text-to-Image Generation via Aesthetic Gradients
Victor Gallego
TL;DR
This paper introduces aesthetic gradients, a technique to customize text-to-image generation by steering the process towards user-defined aesthetics, validated through experiments with stable diffusion models and aesthetic datasets.
Contribution
It presents a novel method for personalizing diffusion-based image generation using aesthetic gradients guided by user-provided images.
Findings
Effective personalization of image aesthetics demonstrated
Qualitative and quantitative validation with stable diffusion models
Code released for reproducibility
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
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Retrieval and Classification Techniques · Aesthetic Perception and Analysis · Video Analysis and Summarization
MethodsDiffusion