DiffBlender: Composable and versatile multimodal text-to-image diffusion models

Sungnyun Kim

doi:10.1016/j.eswa.2025.129345

DiffBlender: Composable and versatile multimodal text-to-image diffusion models

2025-08-19

0

PRE

AI

DOI：10.1016/j.eswa.2025.129345

Original

Original request for help

Save

Abstract

En 中文

• Introduces DiffBlender to unify multiple input modalities—structure, layout, and attribute—within a single T2I framework. • Utilizes a compact “Blender block” that preserves the pre-trained diffusion parameters, minimizing additional training overhead. • Enables efficient multimodal generation and composability across diverse conditions and user preferences. • Proposes mode-specific guidance for precise control over each modality, ensuring balanced and high-fidelity image synthesis.

Keywords:

DiffBlender

multimodal generation

text-to-image synthesis

diffusion models

modality-specific guidance

DiffBlender: Composable and versatile multimodal text-to-image diffusion models

Abstract

Journal

Organization