Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model
This addresses a common failure mode in text-based image editing for users needing precise control, though it appears incremental as it builds on existing attention-based approaches.
The paper tackles the problem of balancing fidelity and editability in text-based image editing, where existing methods lack explicit mechanisms, and introduces UnifyEdit, a tuning-free method that uses diffusion latent optimization with attention-based constraints and an adaptive scheduler to achieve superior balance, outperforming state-of-the-art methods in experiments.
Balancing fidelity and editability is essential in text-based image editing (TIE), where failures commonly lead to over- or under-editing issues. Existing methods typically rely on attention injections for structure preservation and leverage the inherent text alignment capabilities of pre-trained text-to-image (T2I) models for editability, but they lack explicit and unified mechanisms to properly balance these two objectives. In this work, we introduce UnifyEdit, a tuning-free method that performs diffusion latent optimization to enable a balanced integration of fidelity and editability within a unified framework. Unlike direct attention injections, we develop two attention-based constraints: a self-attention (SA) preservation constraint for structural fidelity, and a cross-attention (CA) alignment constraint to enhance text alignment for improved editability. However, simultaneously applying both constraints can lead to gradient conflicts, where the dominance of one constraint results in over- or under-editing. To address this challenge, we introduce an adaptive time-step scheduler that dynamically adjusts the influence of these constraints, guiding the diffusion latent toward an optimal balance. Extensive quantitative and qualitative experiments validate the effectiveness of our approach, demonstrating its superiority in achieving a robust balance between structure preservation and text alignment across various editing tasks, outperforming other state-of-the-art methods. The source code will be available at https://github.com/CUC-MIPG/UnifyEdit.