Poster
in
Workshop: NeurIPS 2023 Workshop on Machine Learning for Creativity and Design
LEDITS++: Limitless Image Editing using Text-to-Image Models
Manuel Brack · Linoy Tsban · Katharina Kornmeier · Apolinário Passos · Felix Friedrich · Patrick Schramowski · Kristian Kersting
Sat 16 Dec 6:15 a.m. PST — 2:40 p.m. PST
Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. Subsequent research efforts are aiming to exploit the capabilities of these models and leverage them for intuitive, textual image editing. However, existing methods often require time-consuming fine-tuning and lack native support for performing multiple edits simultaneously. To address these issues, we introduce LEDITS++, an efficient yet versatile technique for image editing using text-to-image models. LEDITS++ requires no tuning nor optimization, runs in a few diffusion steps, natively supports multiple simultaneous edits, inherently limits changes to relevant image regions, and is architecture agnostic.