Don't Forget your Inverse DDIM for Image Editing
This addresses the challenge of efficient and high-quality image editing for users of text-to-image generation, though it is incremental as it builds upon existing DDIM methods.
The paper tackles the problem of editing real images using diffusion models by introducing SAGE, a technique that leverages pre-trained models with a novel self-attention guidance mechanism, resulting in 47 out of 47 users preferring it over competitors and top performance in 7 out of 10 quantitative analyses.
The field of text-to-image generation has undergone significant advancements with the introduction of diffusion models. Nevertheless, the challenge of editing real images persists, as most methods are either computationally intensive or produce poor reconstructions. This paper introduces SAGE (Self-Attention Guidance for image Editing) - a novel technique leveraging pre-trained diffusion models for image editing. SAGE builds upon the DDIM algorithm and incorporates a novel guidance mechanism utilizing the self-attention layers of the diffusion U-Net. This mechanism computes a reconstruction objective based on attention maps generated during the inverse DDIM process, enabling efficient reconstruction of unedited regions without the need to precisely reconstruct the entire input image. Thus, SAGE directly addresses the key challenges in image editing. The superiority of SAGE over other methods is demonstrated through quantitative and qualitative evaluations and confirmed by a statistically validated comprehensive user study, in which all 47 surveyed users preferred SAGE over competing methods. Additionally, SAGE ranks as the top-performing method in seven out of 10 quantitative analyses and secures second and third places in the remaining three.