LEDITS++: Limitless Image Editing using Text-to-Image Models
This addresses the problem of real image editing for users of text-to-image models, offering a more efficient and versatile solution, though it appears incremental as it builds on prior editing techniques.
The paper tackles the inefficiency, imprecision, and limited versatility of existing text-to-image editing methods by introducing LEDITS++, which requires no tuning, supports multiple simultaneous edits, and uses implicit masking for precise changes, achieving high-fidelity results in few diffusion steps.
Text-to-image diffusion models have recently received increasing interest for their astonishing ability to produce high-fidelity images from solely text inputs. Subsequent research efforts aim to exploit and apply their capabilities to real image editing. However, existing image-to-image methods are often inefficient, imprecise, and of limited versatility. They either require time-consuming finetuning, deviate unnecessarily strongly from the input image, and/or lack support for multiple, simultaneous edits. To address these issues, we introduce LEDITS++, an efficient yet versatile and precise textual image manipulation technique. LEDITS++'s novel inversion approach requires no tuning nor optimization and produces high-fidelity results with a few diffusion steps. Second, our methodology supports multiple simultaneous edits and is architecture-agnostic. Third, we use a novel implicit masking technique that limits changes to relevant image regions. We propose the novel TEdBench++ benchmark as part of our exhaustive evaluation. Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods.