OmniLottie：通过参数化 Lottie 分词器生成矢量动画
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
将 Lottie 矢量动画参数化为函数调用序列，并借助预训练视觉语言模型以多模态指令（文本、图像、视频）为条件进行生成，为矢量图形与动画生成提供了可复用的表示与训练范式。
原文依据 we introduce a dedicated Lottie tokenizer that transforms Lottie files into structured sequences of function calls
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论OmniLottie 是一个通用框架，能够根据多模态指令（包括交错文本、图像和视频）生成高质量的矢量动画。为了将矢量动画完全参数化以实现灵活的运动和视觉内容控制，我们借助 Lottie 表示，它将形状和动画行为编码在单个 JSON 文件中。基于预训练的视觉语言模型（VLM），OmniLottie 生成生动、语义对齐的矢量动画，并紧密遵循多模态条件。为避免原始 JSON 结构的复杂性和不规则性，我们引入了一种专用的 Lottie 分词器，将 Lottie 文件转换为表示形状、动画命令及其参数的结构化函数调用序列。这一设计使模型能够直接从数据中学习潜在的形状和动画先验，显著提高生成稳定性和可控性。为进一步推进矢量动画生成的研究，我们构建了 MMLottie-2M，一个大规模数据集，包含专业设计的矢量动画及其文本和视觉标注。利用精心设计的分词器和新建立的数据集，OmniLottie 通过简单的下一词预测目标展示了强大的多模态条件生成能力。定性结果请参考补充网站中通过标准 Lottie 播放器渲染的生成动画。
英文原文摘要 1477 字符
OmniLottie is a versatile framework that generates high-quality vector animations from multi-modal instructions, including interleaved texts, images, and videos. To fully parameterize vector animations for flexible motion and visual content control, we seek help from the Lottie representation, which encodes both shapes and animated behaviors in a single JSON file. Building upon a pretrained vision-language model (VLM), OmniLottie produces vivid, semantically aligned vector animations that adhere closely to multi-modal conditions. To avoid the complexity and irregularity of raw JSON structures, we introduce a dedicated Lottie tokenizer that transforms Lottie files into structured sequences of function calls representing shapes, animation commands, and their parameters. This design enables the model to directly learn the underlying shape and animation priors from data, substantially improving generation stability and controllability. To further advance research in vector animation generation, we curate MMLottie-2M, a large-scale dataset of professionally designed vector animations paired with textual and visual annotations. Leveraging the well-designed tokenizer and our newly established dataset, OmniLottie demonstrates strong multi-modal conditional generation capabilities using a simple next-token prediction objective. For qualitative results, please refer to the generated animations rendered through standard Lottie players on the supplementary website.