Keyword Weight Rankings for AI-Generated Zhuxian New Year Pictures

A three-layer keyword thesaurus constructed through literature analysis, questionnaire surveys, and semantic clustering supports the digital re-creation of traditional Chinese folk art. The 5.5 KB XLS file contains keyword weight rankings developed by Jiangxu Zhang and was last updated in May 2026. This dataset was built as part of a technical framework combining the Liblib platform and a LoRA model for AI-generated art.

Use Cases

• Fine-tuning text-to-image AI models based on the described three-layer keyword thesaurus.
• Analyzing stylistic feature importance for traditional art digitalization based on keyword weights.
• Designing cultural and graphic creative products based on the integration of traditional aesthetics and modern design mentioned in the study.

Strengths

• Dataset creation involved a three-stage process of image acquisition, multidimensional screening, and expert review.
• Keyword thesaurus was constructed using multiple methods: literature analysis, questionnaire surveys, and semantic clustering.
• The associated model training used a two-stage strategy combining pre-training and fine-tuning with dynamic optimization.

Limitations

• The dataset is very small at 5.5 KB, indicating limited scope.
• Row count and column-level documentation are unknown, which limits suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Jiangxu Zhang

Collection Method

Constructed through literature analysis, questionnaire surveys, and semantic clustering.

Freshness

Last updated 2026-05-27 17:40:40; freshness should be verified.

Geography

Zhuxian Town, China