The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP

TL;DR

This paper demonstrates that CLIP can perform zero-shot disentangled image editing within diffusion models, achieving competitive results and offering a lightweight alternative to traditional editing methods.

Contribution

The study reveals CLIP's capability for zero-shot disentangled editing in diffusion models, a novel insight that enhances image editing flexibility without additional training.

Findings

CLIP enables zero-shot disentangled editing in diffusion models.

The proposed method achieves competitive editing quality.

Potential applications include image and video editing.

Abstract

Diffusion models have become prominent in creating high-quality images. However, unlike GAN models celebrated for their ability to edit images in a disentangled manner, diffusion-based text-to-image models struggle to achieve the same level of precise attribute manipulation without compromising image coherence. In this paper, CLIP which is often used in popular text-to-image diffusion models such as Stable Diffusion is capable of performing disentangled editing in a zero-shot manner. Through both qualitative and quantitative comparisons with state-of-the-art editing methods, we show that our approach yields competitive results. This insight may open opportunities for applying this method to various tasks, including image and video editing, providing a lightweight and efficient approach for disentangled editing.