Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing

TL;DR

This paper presents TODInv, a novel diffusion inversion framework that achieves high-fidelity image reconstruction and precise, task-specific editing by optimizing prompt embeddings across U-Net layers, outperforming existing methods.

Contribution

Introducing TODInv, a hierarchical, task-oriented diffusion inversion method that balances reconstruction fidelity and editability through reciprocal optimization of prompt embeddings.

Findings

Outperforms existing inversion and editing methods quantitatively.

Achieves high-fidelity reconstructions with precise, task-specific edits.

Demonstrates versatility with few-step diffusion models.

Abstract

Recent advancements in text-guided diffusion models have unlocked powerful image manipulation capabilities, yet balancing reconstruction fidelity and editability for real images remains a significant challenge. In this work, we introduce \textbf{T}ask-\textbf{O}riented \textbf{D}iffusion \textbf{I}nversion (\textbf{TODInv}), a novel framework that inverts and edits real images tailored to specific editing tasks by optimizing prompt embeddings within the extended \(\mathcal{P}^*\) space. By leveraging distinct embeddings across different U-Net layers and time steps, TODInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability. This hierarchical editing mechanism categorizes tasks into structure, appearance, and global edits, optimizing only those embeddings unaffected by the current editing task. Extensive experiments on benchmark dataset reveal TODInv's superior performance over existing methods, delivering both quantitative and qualitative enhancements while showcasing its versatility with few-step diffusion model.