LottieGPT: Tokenizing Vector Animation for Autoregressive Generation

• URL: http://arxiv.org/abs/2604.11792v1
• Date: Mon, 13 Apr 2026 17:55:40 GMT
• Title: LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
• Abstract summary: Vector animations offer resolution-independence, compactness, semantic structure, and parametric editable motion representations.<n>Current generative models operate exclusively in space and thus cannot synthesize them.<n>We finetune Qwen-VL to create LottieGPT, a native multimodal model capable of generating coherent, editable vector animations.
• Score: 63.27046904946992
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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).

Related papers

• OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens [56.699545482716736]
  We introduce a well designed Lottie tokenizer that transforms files into structured sequences of commands and parameters representing shapes, animation functions and control parameters.<n>Such tokenizer enables us to build OmniLottie upon pretrained vision language models to follow multi-modal interleaved instructions and generate high quality vector animations.
  arXiv  Detail & Related papers  (2026-03-02T17:59:05Z)
• Animate-X++: Universal Character Image Animation with Dynamic Backgrounds [32.04255747303296]
  Animate-X++ is a universal animation framework based on DiT for various character types, including anthropomorphic characters.<n>To enhance motion representation, we introduce the Pose Indicator, which captures comprehensive motion pattern from the driving video through both implicit and explicit manner.<n>For the second challenge, we introduce a multi-task training strategy that jointly trains the animation and TI2V tasks.
  arXiv  Detail & Related papers  (2025-08-13T03:11:28Z)
• PhysAnimator: Physics-Guided Generative Cartoon Animation [19.124321553546242]
  PhysAnimator is a novel approach for generating anime-stylized animation from static anime illustrations.<n>To capture the fluidity and exaggeration characteristic of anime, we perform image-space deformable body simulations on extracted mesh geometries.<n>We extract and warp sketches from the simulation sequence, generating a texture-agnostic representation, and employ a sketch-guided video diffusion model to synthesize high-quality animation frames.
  arXiv  Detail & Related papers  (2025-01-27T22:48:36Z)
• AniDoc: Animation Creation Made Easier [54.97341104616779]
  Our research focuses on reducing the labor costs in the production of 2D animation by harnessing the potential of increasingly powerful AI.<n>AniDoc emerges as a video line art colorization tool, which automatically converts sketch sequences into colored animations.<n>Our model exploits correspondence matching as an explicit guidance, yielding strong robustness to the variations between the reference character and each line art frame.
  arXiv  Detail & Related papers  (2024-12-18T18:59:59Z)
• Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters [86.13319549186959]
  We present Make-It-Animatable, a novel data-driven method to make any 3D humanoid model ready for character animation in less than one second.<n>Our framework generates high-quality blend weights, bones, and pose transformations.<n>Compared to existing methods, our approach demonstrates significant improvements in both quality and speed.
  arXiv  Detail & Related papers  (2024-11-27T10:18:06Z)
• Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics [79.4785166021062]
  We introduce Puppet-Master, an interactive video generator that captures the internal, part-level motion of objects.<n>We demonstrate that Puppet-Master learns to generate part-level motions, unlike other motion-conditioned video generators.<n>Puppet-Master generalizes well to out-of-domain real images, outperforming existing methods on real-world benchmarks.
  arXiv  Detail & Related papers  (2024-08-08T17:59:38Z)
• AniFormer: Data-driven 3D Animation with Transformer [95.45760189583181]
  We present a novel task, i.e., animating a target 3D object through the motion of a raw driving sequence. AniFormer generates animated 3D sequences by directly taking the raw driving sequences and arbitrary same-type target meshes as inputs. Our AniFormer achieves high-fidelity, realistic, temporally coherent animated results and outperforms compared start-of-the-art methods on benchmarks of diverse categories.
  arXiv  Detail & Related papers  (2021-10-20T12:36:55Z)
• Deep Animation Video Interpolation in the Wild [115.24454577119432]
  In this work, we formally define and study the animation video code problem for the first time. We propose an effective framework, AnimeInterp, with two dedicated modules in a coarse-to-fine manner. Notably, AnimeInterp shows favorable perceptual quality and robustness for animation scenarios in the wild.
  arXiv  Detail & Related papers  (2021-04-06T13:26:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.