ICC Coefficient: Dataset for AI-Generated Digital Re-Creation of Zhuxian New Year Pictures

A dataset supporting research on AI-generated digital re-creation of traditional Chinese folk art. It was created by Jiangxu Zhang and last updated on 2026-05-27. The dataset is 5.5 KB in size and is available in XLS format under a CC-BY-4.0 license.

Use Cases

• Training or evaluating LoRA models for artistic style transfer based on the described framework.
• Analyzing the effectiveness of keyword thesauruses for prompting AI art generation.
• Studying the integration of traditional aesthetics with modern design in graphic creative products.

Strengths

• Dataset was built through a three-stage process of image acquisition, multidimensional screening, and expert review.
• A three-layer keyword thesaurus was constructed using literature analysis, questionnaire surveys, and semantic clustering.
• Model training employed a two-stage strategy combining pre-training and fine-tuning with dynamic optimization.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

figshare, author Jiangxu Zhang.

Collection Method

Built through image acquisition, screening, expert review, and keyword thesaurus construction for a study on AI-generated art.

Freshness

Last updated 2026-05-27 17:40:45; freshness should be verified.

Geography

Focuses on Zhuxian Town, China, as a case study.