DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfer

TL;DR

This paper introduces DIFF-NST, a novel diffusion-based neural style transfer method that enables deformable style transfer, allowing for artistic content deformation, which was difficult with previous models.

Contribution

The paper presents a new diffusion model approach for style transfer that supports deformable transformations, expanding artistic control over content deformation.

Findings

Diffusion models enable new artistic controls during style transfer.

Deformable style transfer is achievable with diffusion-based methods.

The approach offers more flexible style transfer capabilities.

Abstract

Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Traditionally, NST methods have focused on texture-based image edits, affecting mostly low level information and keeping most image structures the same. However, style-based deformation of the content is desirable for some styles, especially in cases where the style is abstract or the primary concept of the style is in its deformed rendition of some content. With the recent introduction of diffusion models, such as Stable Diffusion, we can access far more powerful image generation techniques, enabling new possibilities. In our work, we propose using this new class of models to perform style transfer while enabling deformable style transfer, an elusive capability in previous models. We show how leveraging the priors of these models can expose new artistic controls at inference time, and we document our findings in exploring this new direction for the field of style transfer.