{"ID":2834516,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.01686","arxiv_id":"2512.01686","title":"DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models","abstract":"Current story visualization methods tend to position subjects solely by text and face challenges in maintaining artistic consistency. To address these limitations, we introduce DreamingComics, a layout-aware story visualization framework. We build upon a pretrained video diffusion-transformer (DiT) model, leveraging its spatiotemporal priors to enhance identity and style consistency. For layout-based position control, we propose RegionalRoPE, a region-aware positional encoding scheme that re-indexes embeddings based on the target layout. Additionally, we introduce a masked condition loss to further constrain each subject's visual features to their designated region. To infer layouts from natural language scripts, we integrate an LLM-based layout generator trained to produce comic-style layouts, enabling flexible and controllable layout conditioning. We present a comprehensive evaluation of our approach, showing a 29.2% increase in character consistency and a 36.2% increase in style similarity compared to previous methods, while displaying high spatial accuracy. Our project page is available at https://yj7082126.github.io/dreamingcomics/","short_abstract":"Current story visualization methods tend to position subjects solely by text and face challenges in maintaining artistic consistency. To address these limitations, we introduce DreamingComics, a layout-aware story visualization framework. We build upon a pretrained video diffusion-transformer (DiT) model, leveraging it...","url_abs":"https://arxiv.org/abs/2512.01686","url_pdf":"https://arxiv.org/pdf/2512.01686v1","authors":"[\"Patrick Kwon\",\"Chen Chen\"]","published":"2025-12-01T13:51:41Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\",\"Large Language Model\"]","has_code":false}