OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

An open-source work by OpenVGLab

Yiying Yang^1,2 Wei Cheng^2† Sijin Chen³ Honghao Fu^2,4 XianFang Zeng² Yujun Cai⁴ Gang Yu^2‡ Xinjun Ma^1‡

¹Fudan University ²StepFun ³HKU MMLab ⁴University of Queensland

^†Project Lead ^‡Correspondence Authors

arXiv Code HuggingFace

Model

MMLottie-2M HuggingFace

MMLottie-Bench HuggingFace

Demo

Lottie Parametrization and Generation Process

Generated Lottie Gallery

Introducing OmniLottie

MMLottie-2M Dataset

Overview of the Vector Animation Data Construction Pipeline. Data Collection & Conversion : We convert SVG assets into static Lottie files and apply randomized animation effects to generate effect-tagged animated Lotties. In parallel, we gather professionally created Lottie animations from five online platforms and perform thorough filtering and cleaning. Data Processing : Each animation undergoes spatio-temporal normalization, followed by video rendering and random keyframe extraction. Data Annotation : Finally, we provide multi-granularity annotations emphasizing geometric structure, color attributes, and motion characteristics.

OmniLottie Model

Overview of OmniLottie. Lottie Structure : We reorganize the Lottie JSON representation, with a particular focus on the structure of its layers, including both common layer attributes and five special layer types. Lottie Parametrization : The hierarchical JSON format of Lottie is flattened into a sequence of function calls, which are further parameterized to define a dedicated vocabulary and token set for Lottie. OmniLottie : Built upon this parameterization, OmniLottie extends Qwen2.5-VL with a new tokenizer and vocabulary for Lottie, and is trained on our curated Lottie dataset.

Citation

@article{yang2026omnilottie,
  title={OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens},
  author={Yiying Yang and Wei Cheng and Sijin Chen and Honghao Fu and Xianfang Zeng and Yujun Cai and Gang Yu and Xinjun Ma},
  journal={arXiv preprint arxiv:2603.02138},
  year={2026}
}
}