DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization

TL;DR

DiffStyler introduces a dual diffusion architecture that enables controllable, text-driven image stylization by integrating cross-modal style guidance and content-preserving learnable noise within a diffusion process.

Contribution

The paper proposes DiffStyler, a novel dual diffusion model that effectively combines text guidance with content preservation for stylizing images.

Findings

Outperforms baseline methods in qualitative and quantitative evaluations

Enables precise control over style-content balance

Preserves content structure effectively during stylization

Abstract

Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user. Unlike the previous image-to-image transfer approaches, text-guided stylization progress provides users with a more precise and intuitive way to express the desired style. However, the huge discrepancy between cross-modal inputs/outputs makes it challenging to conduct text-driven image stylization in a typical feed-forward CNN pipeline. In this paper, we present DiffStyler, a dual diffusion processing architecture to control the balance between the content and style of the diffused results. The cross-modal style information can be easily integrated as guidance during the diffusion process step-by-step. Furthermore, we propose a content image-based learnable noise on which the reverse denoising process is based, enabling the stylization results to better preserve the structure information of the content image. We validate the proposed DiffStyler beyond the baseline methods through extensive qualitative and quantitative experiments. Code is available at \url{https://github.com/haha-lisa/Diffstyler}.