Saved in:
Bibliographic Details
Main Authors: Salehi, Sogand, Shafiei, Mahdi, Yeo, Teresa, Bachmann, Roman, Zamir, Amir
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.17365
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917732043194368
author Salehi, Sogand
Shafiei, Mahdi
Yeo, Teresa
Bachmann, Roman
Zamir, Amir
author_facet Salehi, Sogand
Shafiei, Mahdi
Yeo, Teresa
Bachmann, Roman
Zamir, Amir
contents Different users find different images generated for the same prompt desirable. This gives rise to personalized image generation which involves creating images aligned with an individual's visual preference. Current generative models are, however, unpersonalized, as they are tuned to produce outputs that appeal to a broad audience. Using them to generate images aligned with individual users relies on iterative manual prompt engineering by the user which is inefficient and undesirable. We propose to personalize the image generation process by first capturing the generic preferences of the user in a one-time process by inviting them to comment on a small selection of images, explaining why they like or dislike each. Based on these comments, we infer a user's structured liked and disliked visual attributes, i.e., their visual preference, using a large language model. These attributes are used to guide a text-to-image model toward producing images that are tuned towards the individual user's visual preference. Through a series of user studies and large language model guided evaluations, we demonstrate that the proposed method results in generations that are well aligned with individual users' visual preferences.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17365
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ViPer: Visual Personalization of Generative Models via Individual Preference Learning
Salehi, Sogand
Shafiei, Mahdi
Yeo, Teresa
Bachmann, Roman
Zamir, Amir
Computer Vision and Pattern Recognition
Different users find different images generated for the same prompt desirable. This gives rise to personalized image generation which involves creating images aligned with an individual's visual preference. Current generative models are, however, unpersonalized, as they are tuned to produce outputs that appeal to a broad audience. Using them to generate images aligned with individual users relies on iterative manual prompt engineering by the user which is inefficient and undesirable. We propose to personalize the image generation process by first capturing the generic preferences of the user in a one-time process by inviting them to comment on a small selection of images, explaining why they like or dislike each. Based on these comments, we infer a user's structured liked and disliked visual attributes, i.e., their visual preference, using a large language model. These attributes are used to guide a text-to-image model toward producing images that are tuned towards the individual user's visual preference. Through a series of user studies and large language model guided evaluations, we demonstrate that the proposed method results in generations that are well aligned with individual users' visual preferences.
title ViPer: Visual Personalization of Generative Models via Individual Preference Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.17365