# DiffArtist: Towards Structure and Appearance Controllable Image Stylization

Source: [DiffArtist: Towards Structure and Appearance Controllable Image Stylization](<https://www.sota2.com/research/paper/68fa7af91e209131cea860df>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:30:46.040Z

Authors: Ruixiang Jiang, Changwen Chen

Published: 2024-07-22T17:58:05.000Z

## Abstract

Artistic styles are defined by both their structural and appearance elements. Existing neural stylization techniques primarily focus on transferring appearance-level features such as color and texture, often neglecting the equally crucial aspect of structural stylization. To address this gap, we introduce \\textbf{DiffArtist}, the first 2D stylization method to offer fine-grained, simultaneous control over both structure and appearance style strength. This dual controllability is achieved by representing structure and appearance generation as separate diffusion processes, necessitating no further tuning or additional adapters. To properly evaluate this new capability of dual stylization, we further propose a Multimodal LLM-based stylization evaluator that aligns significantly better with human preferences than existing metrics. Extensive analysis shows that DiffArtist achieves superior style fidelity and dual-controllability compared to state-of-the-art methods. Its text-driven, training-free design and unprecedented dual controllability make it a powerful and interactive tool for various creative applications. Project homepage: https://diffusionartist.github.io.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Style Transfer on MS-COCO and WikiArt (1,000 images each)](<https://www.sota2.com/research/sota/style-transfer-on-ms-coco-and-wikiart-1-000-images-each.md>): Style Transfer; MS-COCO and WikiArt 1,000 images each; ArtFID: 16.174.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.15842>)

[PDF](<https://arxiv.org/pdf/2407.15842.pdf>)