Invert Your Prompt: Editing-Aware Diffusion Inversion

Recent advancements in text-guided diffusion models have enabled powerful image manipulation capabilities. However, balancing reconstruction fidelity and editability for real images remains a significant challenge. In this work, we introduce Editing Inversion (EditInv), a novel framework that inverts and edits real images for specific editing tasks by optimizing specific prompt embeddings within the extended P∗ space. By leveraging distinct embeddings across different U-Net layers and time steps, EditInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability. This hierarchical editing mechanism classifies tasks into structure, appearance, and global edits, optimizing only those embeddings that are unaffected by the current editing task. Extensive experiments on benchmark datasets demonstrate EditInv’s superior performance over existing methods, delivering both quantitative and qualitative improvements while showcasing its versatility with a few-step diffusion model.