Skip to content

Source paper

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

Yiying Yang, Wei Cheng, Sijin Chen and 5 more

Yiying Yang, Wei Cheng, Sijin Chen, Honghao Fu, Xianfang Zeng, Yujun Cai, Gang Yu, Xingjun Ma

arXiv 2603.02138 · 2026122 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

This paper presents OmniLottie, an end-to-end framework leveraging a multimodal Large Language Model (Qwen2.5-VL) to generate Lottie vector animations from text, images, or video instructions. The authors introduce a specialized "Lottie Tokenizer" to compress complex JSON structures into efficient command sequences and release MMLottie-2M, a large-scale dataset of vector animations, to train the model for high visual fidelity and semantic alignment.

How it works (AI summary)

The core methodology involves a custom Lottie Tokenizer that converts hierarchical JSON files into linear, quantized command sequences to remove redundant metadata. These token sequences are then used to fine-tune Qwen2.5-VL in an autoregressive manner, enabling the model to predict vector animation parameters directly from interleaved multimodal inputs.