Zhuxian New Year Pictures Dataset for AI-Generated Digital Re-Creation

A dataset supporting the AI-generated digital re-creation of traditional Chinese Zhuxian Town New Year pictures. It was created by Jiangxu Zhang and last updated on 2026-05-27. The dataset was built through a three-stage process of image acquisition, multidimensional screening, and expert review.

Use Cases

• Training LoRA models for style transfer based on the described stylistic features of Zhuxian New Year pictures.
• Developing cultural and graphic creative products based on the integration of traditional aesthetics with modern design.
• Studying the construction of a three-layer keyword thesaurus for traditional art datasets.
• Evaluating two-stage training strategies combining pre-training and fine-tuning for artistic style capture.

Strengths

• Dataset construction involved a three-stage process including expert review, suggesting quality control.
• A three-layer keyword thesaurus was constructed through literature analysis, questionnaire surveys, and semantic clustering.
• The dataset is associated with a specific technical framework combining the Liblib platform and a LoRA model.

Limitations

• Dataset size is 5.5 KB, indicating a very limited scope.
• Row count and column-level documentation are unknown, which limits suitability assessment.
• Description metadata is limited; actual data quality and structure require manual inspection after download.

Provenance

Source

Author: Jiangxu Zhang. Platform: figshare.

Collection Method

Built through a three-stage process of image acquisition, multidimensional screening, and expert review.

Freshness

Last updated 2026-05-27 17:40:49; freshness should be verified.

Geography

Focuses on New Year pictures from China's Zhuxian Town.