DiffArtist: Towards Structure and Appearance Controllable Image Stylization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jiang, Ruixiang, Chen, Changwen
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911123402391552
author Jiang, Ruixiang
Chen, Changwen
author_facet Jiang, Ruixiang
Chen, Changwen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15842
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffArtist: Towards Structure and Appearance Controllable Image Stylization
Jiang, Ruixiang
Chen, Changwen
Computer Vision and Pattern Recognition
Graphics
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.
title DiffArtist: Towards Structure and Appearance Controllable Image Stylization
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2407.15842