X-Dance: Harmonized Human Image Animation with First-Frame Preservation

SteadyDancer is a dataset for human image animation, focusing on harmonized and coherent motion generation while preserving the first frame. It was created by researchers from Nanjing University and Tencent and was last updated on November 27, 2025. The dataset likely contains sequences of human images or videos for training and evaluating animation models.

Use Cases

• Training models for coherent human video generation based on the described focus on harmonized animation.
• Evaluating image animation techniques based on the first-frame preservation property mentioned in the description.
• Benchmarking methods for human motion synthesis based on the dataset's stated purpose for human image animation.

Strengths

• Created by a collaboration between Nanjing University's Multimedia Computing Group and Tencent's Platform and Content Group, suggesting academic and industry expertise.
• Focus on specific technical challenges like harmonization and first-frame preservation indicates a curated purpose.

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 and file size are unknown, which may limit suitability assessment.

Provenance

Source

Multimedia Computing Group, Nanjing University and Platform and Content Group (PCG), Tencent

Freshness

Last updated 2025-11-27 03:15:33; freshness should be verified.