Zhuxian New Year Pictures Dataset for AI Art Generation

A high-quality dataset built through a three-stage process of image acquisition, screening, and expert review for AI-generated digital re-creation of traditional Chinese folk art. The dataset was created by Jiangxu Zhang and last updated on 2026-05-27. It is used to train a LoRA model that captures the stylistic features of Zhuxian Town New Year pictures.

Use Cases

• Fine-tuning generative AI models for traditional art style transfer based on the described high-quality image dataset.
• Developing cultural and graphic creative products based on AI-generated outputs that integrate traditional aesthetics.
• Studying cross-domain innovation in folk art digitalization based on the described collaborative technical framework.
• Training models for artistic style preservation based on the described three-layer keyword thesaurus and two-stage training strategy.

Strengths

• Dataset construction involved a three-stage process including expert review, suggesting quality control.
• A three-layer keyword thesaurus was constructed using literature analysis, surveys, and semantic clustering.
• The model training employed a two-stage strategy with dynamic optimization to capture stylistic features.

Limitations

• Dataset size is only 5.5 KB, indicating a very limited scope.
• Row count and column-level documentation are unknown, limiting suitability assessment.
• The description focuses on the research framework; the specific content and structure of the data file are not detailed.

Provenance

Source

Jiangxu Zhang via figshare.

Collection Method

Built through image acquisition, multidimensional screening, and expert review.

Freshness

Last updated 2026-05-27 17:40:50; freshness should be verified.

Geography

Focuses on Zhuxian Town, China.