Saved in:
Bibliographic Details
Main Authors: Kim, Hyungjin, Ahn, Seokho, Seo, Young-Duk
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.03481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908479324684288
author Kim, Hyungjin
Ahn, Seokho
Seo, Young-Duk
author_facet Kim, Hyungjin
Ahn, Seokho
Seo, Young-Duk
contents Personalized generation in T2I diffusion models aims to naturally incorporate individual user preferences into the generation process with minimal user intervention. However, existing studies primarily rely on prompt-level modeling with large-scale models, often leading to inaccurate personalization due to the limited input token capacity of T2I diffusion models. To address these limitations, we propose DrUM, a novel method that integrates user profiling with a transformer-based adapter to enable personalized generation through condition-level modeling in the latent space. DrUM demonstrates strong performance on large-scale datasets and seamlessly integrates with open-source text encoders, making it compatible with widely used foundation T2I models without requiring additional fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03481
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models
Kim, Hyungjin
Ahn, Seokho
Seo, Young-Duk
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Personalized generation in T2I diffusion models aims to naturally incorporate individual user preferences into the generation process with minimal user intervention. However, existing studies primarily rely on prompt-level modeling with large-scale models, often leading to inaccurate personalization due to the limited input token capacity of T2I diffusion models. To address these limitations, we propose DrUM, a novel method that integrates user profiling with a transformer-based adapter to enable personalized generation through condition-level modeling in the latent space. DrUM demonstrates strong performance on large-scale datasets and seamlessly integrates with open-source text encoders, making it compatible with widely used foundation T2I models without requiring additional fine-tuning.
title Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2508.03481