DiffStyle360: Diffusion-Based 360{\deg} Head Stylization via Style Fusion Attention

TL;DR

DiffStyle360 is a diffusion-based method for 3D head stylization that produces multi-view consistent, identity-preserving results from a single style image without needing per-style training.

Contribution

It introduces a style fusion attention mechanism and a style appearance module, enabling style transfer without extensive optimization or fine-tuning.

Findings

Outperforms state-of-the-art stylization methods in style quality.

Achieves multi-view consistency and identity preservation.

Operates effectively across diverse artistic styles.

Abstract

3D head stylization has emerged as a key technique for reimagining realistic human heads in various artistic forms, enabling expressive character design and creative visual experiences in digital media. Despite the progress in 3D-aware generation, existing 3D head stylization methods often rely on computationally expensive optimization or domain-specific fine-tuning to adapt to new styles. To address these limitations, we propose DiffStyle360, a diffusion-based framework capable of producing multi-view consistent, identity-preserving 3D head stylizations across diverse artistic domains given a single style reference image, without requiring per-style training. Building upon the 3D-aware DiffPortrait360 architecture, our approach introduces two key components: the Style Appearance Module, which disentangles style from content, and the Style Fusion Attention mechanism, which adaptively balances structure preservation and stylization fidelity in the latent space. Furthermore, we employ a 3D GAN-generated multi-view dataset for robust fine-tuning and introduce a temperaturebased key scaling strategy to control stylization intensity during inference. Extensive experiments on FFHQ and RenderMe360 demonstrate that DiffStyle360 achieves superior style quality, outperforming state-of-the-art GAN- and diffusion-based stylization methods across challenging style domains.