We propose a diffusion-based framework for zero-shot image editing that unifies text-guided and reference-guided approaches without requiring fine-tuning. Our method leverages diffusion inversion and timestep-specific null-text embeddings to preserve the structural integrity of the source image. By introducing a stage-wise latent injection strategy-shape injection in early steps and attribute injection in later steps-we enable precise, fine-grained modifications while maintaining global consistency. Cross-attention with reference latents facilitates semantic alignment between the source and reference. Extensive experiments across expression transfer, texture transformation, and style infusion demonstrate state-of-the-art performance, confirming the method's scalability and adaptability to diverse image editing scenarios.
@article{arxiv.2504.15723,
title = {Structure-Preserving Zero-Shot Image Editing via Stage-Wise Latent Injection in Diffusion Models},
author = {Dasol Jeong and Donggoo Kang and Jiwon Park and Hyebean Lee and Joonki Paik},
journal= {arXiv preprint arXiv:2504.15723},
year = {2025}
}