LottieGPT: 660K Vector Animations for Autoregressive Generation

LottieGPT is a model for generating editable vector animations in an autoregressive manner. The associated dataset, LottieAnimation-660K, likely contains a large collection of vector animation sequences used to train this model. It was created by researchers from Tsinghua University, BAAI, and other institutions, and was last updated on the platform in June 2026.

Use Cases

• Training autoregressive models for vector animation generation based on the described model purpose.
• Benchmarking generative AI performance on structured, editable graphics data.
• Studying the tokenization and representation of vector graphics for machine learning.

Strengths

• Dataset is associated with a model from a major research institution (Tsinghua University).
• The description indicates a focus on editable vector output, a distinctive feature for generative tasks.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file formats are unknown, which may limit suitability assessment.

Provenance

Source

LottieGPT

Freshness

Last updated 2026-06-04 11:23:32; freshness should be verified.