2024/07/22 by Ruixiang Jiang, Chang Wen Chen, Jiang, Ruixiang +1 · 1 citation
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR) #Handwritten Text Recognition Techniques #Human Motion and Animation #Natural Language Processing Techniques
paper · pdf · doi:10.48550/arxiv.2407.15842
openalex publication_date 2024/07/22 · openalex created_date 2024/12/25 · openalex updated_date 2026/08/01
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 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.