EffectMaker：统一推理与生成实现定制化视觉效果创作
EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation
用多模态大语言模型做高层特效语义推理、扩散 Transformer 通过上下文学习从参考视频提取细粒度视觉线索，形成语义-视觉双路引导，实现无需逐特效微调的参考驱动视频特效合成，可直接迁移到风格化视频编辑与参考引导的可控生成。
原文依据 a diffusion transformer leverages in-context learning to capture fine-grained visual cues from reference videos
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉效果（VFX）对于增强视频内容的表现力与创造力至关重要，但制作高质量特效通常需要专业知识与昂贵的制作流程。现有 AIGC 系统在 VFX 生成上面临显著挑战，原因在于特效专用数据的稀缺，以及建模超现实或风格化特效的内在困难。此外，这些方法往往需要针对每种特效进行微调，严重限制了其可扩展性与对新特效的泛化能力。在本工作中，我们提出 EffectMaker，一个统一的推理-生成框架，可实现基于参考的 VFX 定制。EffectMaker 采用多模态大语言模型来解读高层特效语义，并推理这些语义应如何适配目标主体，同时由扩散 Transformer 利用上下文学习从参考视频中捕捉细粒度视觉线索。这两个组件构成语义-视觉双路引导机制，从而在无需逐特效微调的情况下实现准确、可控且特效一致的合成。此外，我们构建了 EffectData，这是迄今规模最大的高质量合成 VFX 数据集，包含 3k 个 VFX 类别下的 130k 段视频，以提升泛化性与可扩展性。实验表明，EffectMaker 在视觉质量与特效一致性上优于最优基线方法，为定制化 VFX 生成提供了一种可扩展且灵活的范式。项目主页：https://effectmaker.github.io。
英文原文摘要 1530 字符
Visual effects (VFX) are essential for enhancing the expressiveness and creativity of video content, yet producing high-quality effects typically requires expert knowledge and costly production pipelines. Existing AIGC systems face significant challenges in VFX generation due to the scarcity of effect-specific data and the inherent difficulty of modeling supernatural or stylized effects. Moreover, these approaches often require per-effect fine-tuning, which severely limits their scalability and generalization to novel VFX. In this work, we present EffectMaker, a unified reasoning-generation framework that enables reference-based VFX customization. EffectMaker employs a multimodal large language model to interpret high-level effect semantics and reason about how they should adapt to a target subject, while a diffusion transformer leverages in-context learning to capture fine-grained visual cues from reference videos. These two components form a semantic-visual dual-path guidance mechanism that enables accurate, controllable, and effect-consistent synthesis without per-effect fine-tuning. Furthermore, we construct EffectData, the largest high-quality synthetic VFX dataset to date, containing 130k videos across 3k VFX categories, to improve generalization and scalability. Experiments show that EffectMaker achieves superior visual quality and effect consistency over state-of-the-art baselines, offering a scalable and flexible paradigm for customized VFX generation. Project page: https://effectmaker.github.io.