Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models
Year: 2025
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Kim, Hyungjin, Ahn, Seokho, Seo, Young-Duk
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7077070126
Cites:
Cited by:
Related to: