BRE_S01: Original and AI-Generated Video Scenes for Style Analysis

BRE_S01 Dataset for Generative AI Video Style Analysis contains scene-level video materials for a comparative analysis of original and AI-generated videos. The dataset includes RAW and PRE videos, prompt files, generation settings, and metadata for the 1960 French New Wave film 'Breathless'. Jinyu Kim created this 86.9 MB dataset, last updated on 2026-06-04, as part of a doctoral dissertation project.

Use Cases

• Compare original and AI-generated video styles based on the provided RAW and PRE video pairs.
• Analyze the effect of different generation settings on output based on the included settings files.
• Study prompt engineering for video generation based on the provided prompt files.
• Conduct scene-level stylistic analysis of AI-generated film content based on the standardized 720p, 24 fps, 8-second PRE videos.

Strengths

• Includes both RAW generated videos and standardized PRE videos (720p, 24 fps, 8 seconds) for consistent analysis.
• Provides associated metadata, prompt files, and generation settings, offering context for the AI-generated content.
• Focuses on a specific, well-defined film ('Breathless', 1960) and style (French New Wave) for controlled study.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Audio is excluded from the analysis, limiting the scope of multimodal style study.

Provenance

Source

Jinyu Kim

Collection Method

Part of a doctoral dissertation project on reconfiguring film styles through generative AI video models.

Time Range

Based on the 1960 film 'Breathless'.

Freshness

Last updated 2026-06-04 20:59:09; freshness should be verified.