MOTIA is a diffusion-based method for open-domain video outpainting, capable of handling arbitrary mask types, video resolutions, and styles. It leverages the intrinsic data-specific patterns of the source video and image/video generative prior to achieve high-quality outpainting. The method consists of two main phases: input-specific adaptation and pattern-aware outpainting. During input-specific adaptation, the model learns patterns from the source video through pseudo-outpainting learning, enabling it to bridge the gap between standard generation and outpainting. In the pattern-aware outpainting phase, these learned patterns are generalized to generate outpainting outcomes. Additional strategies, such as spatial-aware insertion and noise travel, are proposed to better leverage the diffusion model's generative prior and the acquired video patterns. Extensive evaluations show that MOTIA outperforms existing state-of-the-art methods in widely recognized benchmarks. The method achieves significant improvements in both quantitative metrics and user studies, demonstrating its effectiveness in video outpainting. MOTIA's input-specific adaptation allows the model to better capture the size, length, and style distribution of the source video, narrowing the gap between pretrained weights and the source video. The method also effectively captures intrinsic patterns from the source video, leading to superior outpainting results. The model's performance is validated through extensive experiments, showing significant improvements in video quality, perceptual metrics, and distribution similarity. The method is also extended to long video outpainting, where it efficiently handles long videos by sampling short video clips for adaptation. The model's effectiveness is further supported by ablation studies, which show that each component of the method contributes to improved performance. The method is compared to other approaches in user studies, where it is preferred for both visual quality and realism. Overall, MOTIA demonstrates significant advancements in video outpainting, achieving state-of-the-art results while maintaining flexibility and efficiency.MOTIA is a diffusion-based method for open-domain video outpainting, capable of handling arbitrary mask types, video resolutions, and styles. It leverages the intrinsic data-specific patterns of the source video and image/video generative prior to achieve high-quality outpainting. The method consists of two main phases: input-specific adaptation and pattern-aware outpainting. During input-specific adaptation, the model learns patterns from the source video through pseudo-outpainting learning, enabling it to bridge the gap between standard generation and outpainting. In the pattern-aware outpainting phase, these learned patterns are generalized to generate outpainting outcomes. Additional strategies, such as spatial-aware insertion and noise travel, are proposed to better leverage the diffusion model's generative prior and the acquired video patterns. Extensive evaluations show that MOTIA outperforms existing state-of-the-art methods in widely recognized benchmarks. The method achieves significant improvements in both quantitative metrics and user studies, demonstrating its effectiveness in video outpainting. MOTIA's input-specific adaptation allows the model to better capture the size, length, and style distribution of the source video, narrowing the gap between pretrained weights and the source video. The method also effectively captures intrinsic patterns from the source video, leading to superior outpainting results. The model's performance is validated through extensive experiments, showing significant improvements in video quality, perceptual metrics, and distribution similarity. The method is also extended to long video outpainting, where it efficiently handles long videos by sampling short video clips for adaptation. The model's effectiveness is further supported by ablation studies, which show that each component of the method contributes to improved performance. The method is compared to other approaches in user studies, where it is preferred for both visual quality and realism. Overall, MOTIA demonstrates significant advancements in video outpainting, achieving state-of-the-art results while maintaining flexibility and efficiency.