English

Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models

Computer Vision and Pattern Recognition 2025-08-06 v1 Artificial Intelligence Computation and Language

Abstract

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.

Keywords

Cite

@article{arxiv.2508.03481,
  title  = {Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models},
  author = {Hyungjin Kim and Seokho Ahn and Young-Duk Seo},
  journal= {arXiv preprint arXiv:2508.03481},
  year   = {2025}
}

Comments

Accepted at ICCV 2025

R2 v1 2026-07-01T04:35:14.545Z