DreamShot：基于视频扩散先验的个性化故事板合成
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
利用视频扩散先验进行多镜头故事板合成，通过多参考角色条件模块和角色注意力一致性损失显式约束参考与生成角色间的注意力，为可控视频生成中的角色一致性提供可复用技术。
原文依据 DreamShot incorporates a multi-reference role conditioning module that accepts multiple character reference images and enforces identity alignment via a Role-Attention Consistency Loss
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论故事板合成在视觉叙事中起着至关重要的作用，旨在生成连贯的镜头序列，以一致的角色、场景和转场来视觉化叙述电影事件。然而，现有方法大多改编自文本到图像扩散模型，难以在多个镜头间保持长程时序连贯性、一致的角色身份和叙事流。本文提出DreamShot，一种基于视频生成模型的故事板框架，充分利用强大的视频扩散先验进行可控的多镜头合成。DreamShot支持文本到镜头和参考到镜头的生成，以及基于先前帧的故事延续，从而实现灵活且上下文感知的故事板生成。通过利用视频生成模型固有的时空一致性，DreamShot生成视觉和语义上连贯的序列，具有改进的叙事保真度和角色连续性。此外，DreamShot集成了一个多参考角色条件模块，接受多个角色参考图像，并通过角色注意力一致性损失强制身份对齐，显式约束参考角色与生成角色之间的注意力。大量实验表明，与最优的文本到图像故事板模型相比，DreamShot实现了更优的场景连贯性、角色一致性和生成效率，为可控视频模型驱动的视觉叙事开辟了新方向。
英文原文摘要 1550 字符
Storyboard synthesis plays a crucial role in visual storytelling, aiming to generate coherent shot sequences that visually narrate cinematic events with consistent characters, scenes, and transitions. However, existing approaches are mostly adapted from text-to-image diffusion models, which struggle to maintain long-range temporal coherence, consistent character identities, and narrative flow across multiple shots. In this paper, we introduce DreamShot, a video generative model based storyboard framework that fully exploits powerful video diffusion priors for controllable multi-shot synthesis. DreamShot supports both Text-to-Shot and Reference-to-Shot generation, as well as story continuation conditioned on previous frames, enabling flexible and context-aware storyboard generation. By leveraging the spatial-temporal consistency inherent in video generative models, DreamShot produces visually and semantically coherent sequences with improved narrative fidelity and character continuity. Furthermore, DreamShot incorporates a multi-reference role conditioning module that accepts multiple character reference images and enforces identity alignment via a Role-Attention Consistency Loss, explicitly constraining attention between reference and generated roles. Extensive experiments demonstrate that DreamShot achieves superior scene coherence, role consistency, and generation efficiency compared to state-of-the-art text-to-image storyboard models, establishing a new direction toward controllable video model-driven visual storytelling.