NOS_S01: Scene-Level Video Materials for AI-Generated Film Style Analysis

44.4 MB of scene-level video materials from the 1922 film 'Nosferatu: A Symphony of Horror' used in a doctoral dissertation on generative AI. The dataset includes RAW and PRE-processed videos at 720p, 24 fps, and 8 seconds, alongside prompt files, generation settings, and metadata. Author Jinyu Kim released it under a CC-BY-4.0 license on figshare in June 2026.

Use Cases

• Comparative visual analysis based on original and AI-generated video pairs.
• Benchmarking generative AI video models based on standardized 720p, 24 fps, 8-second clips.
• Studying the reconfiguration of German Expressionist film style based on AI-generated materials.
• Analyzing the relationship between text prompts and generated video outputs based on provided prompt files.

Strengths

• Includes both RAW generated videos and standardized PRE-processed clips at 720p, 24 fps, and 8 seconds for consistent analysis.
• Contains auxiliary data like prompt files and generation settings, which are crucial for reproducibility in AI video research.
• Focuses on a single, well-defined film ('Nosferatu', 1922) and style (German Expressionism) for a controlled case study.

Limitations

• Row count is unknown, which may limit suitability assessment for large-scale machine learning tasks.
• Column-level documentation is absent; field semantics must be inferred after download.
• Audio is excluded from the analysis, limiting the dataset to visual style study only.

Provenance

Source

Part of a doctoral dissertation project by Jinyu Kim.

Collection Method

Likely contains videos generated by AI models from original film scenes, as described for comparative analysis.

Time Range

Source film released in 1922.

Freshness

Last updated 2026-06-04 21:00:47; freshness should be verified.