Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer from semantic entanglement, including concept entanglement and improper attribute binding, leading to significant text-image inconsistency. We identify that semantic entanglement arises when certain regions of the latent features attend to incorrect concept and attribute tokens. In this work, we propose the Semantic Protection Diffusion Model (SPDiffusion) to address both concept entanglement and improper attribute binding using only a text prompt as input. The SPDiffusion framework introduces a novel concept region extraction method SP-Extraction to resolve region entanglement in cross-attention, along with SP-Attn, which protects concept regions from the influence of irrelevant attributes and concepts. To evaluate our method, we test it on existing benchmarks, where SPDiffusion achieves state-of-the-art results, demonstrating its effectiveness.
View on arXiv@article{zhang2025_2409.01327,
title={ SPDiffusion: Semantic Protection Diffusion Models for Multi-concept Text-to-image Generation },
author={ Yang Zhang and Rui Zhang and Xuecheng Nie and Haochen Li and Jikun Chen and Yifan Hao and Xin Zhang and Luoqi Liu and Ling Li },
journal={arXiv preprint arXiv:2409.01327},
year={ 2025 }
}