{"ID":2888331,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03735","arxiv_id":"2508.03735","title":"StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization","abstract":"Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically rely on fine-tuning or retraining models, are computationally expensive, time-consuming, and often interfere with the model's pre-existing capabilities. In this paper, we follow a training-free approach and propose an efficient consistent-subject-generation method. This approach works seamlessly with pre-trained diffusion models by introducing masked cross-image attention sharing to dynamically align subject features across a batch of images, and Regional Feature Harmonization to refine visually similar details for improved subject consistency. Experimental results demonstrate that our approach successfully generates visually consistent subjects across a variety of scenarios while maintaining the creative abilities of the diffusion model.","short_abstract":"Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically rely on fine-tuning or retraining models, are computationally expensive, time-cons...","url_abs":"https://arxiv.org/abs/2508.03735","url_pdf":"https://arxiv.org/pdf/2508.03735v1","authors":"[\"Gopalji Gaur\",\"Mohammadreza Zolfaghari\",\"Thomas Brox\"]","published":"2025-07-31T11:24:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}