SINE: SINgle Image Editing with Text-to-Image Diffusion Models

TL;DR

SINE introduces a novel single-image editing method using diffusion models, leveraging model-based guidance and patch-based fine-tuning to enable diverse and high-resolution edits without overfitting.

Contribution

It proposes a new guidance technique and patch-based fine-tuning for effective single-image editing with diffusion models, overcoming overfitting and content leakage issues.

Findings

Effective style and content editing demonstrated

High-resolution image generation achieved

Model-guided approach outperforms fine-tuning methods

Abstract

Recent works on diffusion models have demonstrated a strong capability for conditioning image generation, e.g., text-guided image synthesis. Such success inspires many efforts trying to use large-scale pre-trained diffusion models for tackling a challenging problem--real image editing. Works conducted in this area learn a unique textual token corresponding to several images containing the same object. However, under many circumstances, only one image is available, such as the painting of the Girl with a Pearl Earring. Using existing works on fine-tuning the pre-trained diffusion models with a single image causes severe overfitting issues. The information leakage from the pre-trained diffusion models makes editing can not keep the same content as the given image while creating new features depicted by the language guidance. This work aims to address the problem of single-image editing. We propose a novel model-based guidance built upon the classifier-free guidance so that the knowledge from the model trained on a single image can be distilled into the pre-trained diffusion model, enabling content creation even with one given image. Additionally, we propose a patch-based fine-tuning that can effectively help the model generate images of arbitrary resolution. We provide extensive experiments to validate the design choices of our approach and show promising editing capabilities, including changing style, content addition, and object manipulation. The code is available for research purposes at https://github.com/zhang-zx/SINE.git .