LEDITS++: Limitless Image Editing using Text-to-Image Models

arXiv:2311.16711v2 Announce Type: replace-cross
Abstract: 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 …

abstract aim apply arxiv capabilities cs.ai cs.cv cs.hc cs.lg diffusion diffusion models editing exploit fidelity however image image diffusion images image-to-image inputs limitless replace research text text-to-image type