Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing
This addresses a bottleneck in text-conditional image editing for AIGC applications, offering a training- and tuning-free solution with incremental improvements over existing methods.
The paper tackles the problem of reconstruction failure in DDIM Inversion for real image editing, proposing Dual-Schedule Inversion to achieve perfect reconstruction without fine-tuning and superior editing performance with semantic alignment and identity retention.
Text-conditional image editing is a practical AIGC task that has recently emerged with great commercial and academic value. For real image editing, most diffusion model-based methods use DDIM Inversion as the first stage before editing. However, DDIM Inversion often results in reconstruction failure, leading to unsatisfactory performance for downstream editing. To address this problem, we first analyze why the reconstruction via DDIM Inversion fails. We then propose a new inversion and sampling method named Dual-Schedule Inversion. We also design a classifier to adaptively combine Dual-Schedule Inversion with different editing methods for user-friendly image editing. Our work can achieve superior reconstruction and editing performance with the following advantages: 1) It can reconstruct real images perfectly without fine-tuning, and its reversibility is guaranteed mathematically. 2) The edited object/scene conforms to the semantics of the text prompt. 3) The unedited parts of the object/scene retain the original identity.