LottieGPT is a model for generating editable vector animations in an autoregressive manner. The dataset likely contains vector animation data used to train this model, created by researchers from Tsinghua University, BAAI, The Hong Kong Polytechnic University, Nanjing University, and Guangming Lab. The dataset page was last updated on June 4, 2026.
Use Cases
- Training autoregressive models for vector animation generation based on the dataset's animation sequences.
- Benchmarking generative AI performance on structured, editable graphics data.
- Developing tools for converting raster frames to vector animations based on the dataset's content.
Strengths
- Dataset is associated with a model from a consortium of major academic institutions.
- Focuses on editable vector animations, a distinct format from raster frames.
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 is unknown, which may limit suitability assessment.
Provenance
- Source
- LottieGPT