LottieGPT：面向自回归生成的矢量动画词元化
LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
将矢量动画（Lottie JSON）通过定制分词器编码为紧凑词元序列，并微调 Qwen-VL 实现自回归生成，为视觉生成提供了一种超越栅格空间、直接输出可编辑结构化数据的新范式。
原文依据 we present the first framework for tokenizing and autoregressively generating vector animations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管视频生成取得了快速进展，现有模型仍无法生成矢量动画——一种在互联网上占据主导且极具表现力的多媒体形式。矢量动画具有分辨率无关性、紧凑性、语义结构以及可编辑的参数化运动表示，然而当前的生成模型仅在栅格空间中运作，因而无法合成它们。与此同时，大型多模态模型的最新进展在生成幻灯片、3D网格、乐高序列和室内布局等结构化数据方面展现出强大能力，这表明原生矢量动画生成或许是可以实现的。在本工作中，我们提出了首个用于词元化并自回归生成矢量动画的框架。我们采用Lottie——一种广泛部署的基于JSON的动画标准，并设计了定制的Lottie分词器，将分层几何基元、变换以及基于关键帧的运动编码为紧凑且语义对齐的词元序列。为支持大规模训练，我们还构建了LottieAnimation-660K，这是迄今为止规模最大、最多样化的矢量动画数据集，包含从广泛互联网来源中整理的66万个真实世界Lottie动画和1500万个静态Lottie图像文件。基于这些组件，我们微调Qwen-VL创建了LottieGPT，这是一个原生多模态模型，能够直接从自然语言或视觉提示生成连贯、可编辑的矢量动画。实验表明，我们的分词器在保持结构保真度的同时大幅缩短了序列长度，从而实现了对动态矢量内容的有效自回归学习。LottieGPT在多样化的动画风格上展现出强大的泛化能力，并在SVG生成（单帧矢量动画的一种特例）上超越了此前的最优模型。
英文原文摘要 1842 字符
Despite rapid progress in video generation, existing models are incapable of producing vector animation, a dominant and highly expressive form of multimedia on the Internet. Vector animations offer resolution-independence, compactness, semantic structure, and editable parametric motion representations, yet current generative models operate exclusively in raster space and thus cannot synthesize them. Meanwhile, recent advances in large multimodal models demonstrate strong capabilities in generating structured data such as slides , 3D meshes , LEGO sequences , and indoor layouts , suggesting that native vector animation generation may be achievable. In this work, we present the first framework for tokenizing and autoregressively generating vector animations. We adopt Lottie, a widely deployed JSON-based animation standard, and design a tailored Lottie Tokenizer that encodes layered geometric primitives, transforms, and keyframe-based motion into a compact and semantically aligned token sequence. To support large-scale training, we also construct LottieAnimation-660K, the largest and most diverse vector animation dataset to date, consisting of 660k real-world Lottie animation and 15M static Lottie image files curated from broad Internet sources. Building upon these components, we finetune Qwen-VL to create LottieGPT, a native multimodal model capable of generating coherent, editable vector animations directly from natural language or visual prompts. Experiments show that our tokenizer dramatically reduces sequence length while preserving structural fidelity, enabling effective autoregressive learning of dynamic vector content. LottieGPT exhibits strong generalization across diverse animation styles and outperforms previous state-of-the-art models on SVG generation (a special case of single-frame vector animation).