GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models

arXiv:2403.19645v1 Announce Type: new
Abstract: The rapid advancement in image generation models has predominantly been driven by diffusion models, which have demonstrated unparalleled success in generating high-fidelity, diverse images from textual prompts. Despite their success, diffusion models encounter substantial challenges in the domain of image editing, particularly in executing disentangled edits-changes that target specific attributes of an image while leaving irrelevant parts untouched. In contrast, Generative Adversarial Networks (GANs) have been recognized for their success in disentangled edits through their …

abstract advancement arxiv challenges cs.cv diffusion diffusion models diverse domain editing fidelity gan image image diffusion image generation image generation models images prompts success text text-to-image textual transfer type