iMontage：统一、多功能、高度动态的多对多图像生成
iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation
AI总结：
iMontage通过整合视频模型的先验知识与图像数据的多样性，实现了统一、多功能且动态的多对多图像生成。
摘要：
预训练视频模型学习了强大的先验知识，用于生成高质量且时间上一致的内容。尽管这些模型在时间一致性方面表现出色，但它们的动力性往往受到连续训练数据的限制。我们假设通过将图像数据中丰富的、无约束的内容多样性注入到这个一致的时间框架中，可以生成具有自然过渡和更广阔动态范围的图像集。为此，我们介绍了iMontage，一个统一的框架，旨在将强大的视频模型重新利用为一个全能的图像生成器。该框架消耗和产生可变长度的图像集，统一了广泛的一系列图像生成和编辑任务。为此，我们提出了一种优雅且最小侵入性的适应策略，辅以定制的数据整理过程和训练范式。这种方法使模型能够获得广泛图像处理能力，而不会破坏其宝贵的原始运动先验。iMontage在多个主流多对多任务中表现出色，不仅保持了跨图像的上下文一致性，还生成了具有非凡动态性的场景，超越了传统范围。访问我们的主页：https://kr1sjfu.github.io/iMontage-web/。
英文摘要：
Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data. We hypothesize that by injecting the rich and unconstrained content diversity from image data into this coherent temporal framework, we can generate image sets that feature both natural transitions and a far more expansive dynamic range. To this end, we introduce iMontage, a unified framework designed to repurpose a powerful video model into an all-in-one image generator. The framework consumes and produces variable-length image sets, unifying a wide array of image generation and editing tasks. To achieve this, we propose an elegant and minimally invasive adaptation strategy, complemented by a tailored data curation process and training paradigm. This approach allows the model to acquire broad image manipulation capabilities without corrupting its invaluable original motion priors. iMontage excels across several mainstream many-in-many-out tasks, not only maintaining strong cross-image contextual consistency but also generating scenes with extraordinary dynamics that surpass conventional scopes. Find our homepage at: https://kr1sjfu.github.io/iMontage-web/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
