JSON Layered Video Compositions Dataset
Access a large-scale library of more than 700,000 layered video compositions representing structured visual scenes rather than flattened video outputs. Each composition typically contains 2–4 independently rendered visual layers, including base video, HUD graphics, overlays, atmospheric effects, flares, particles, bokeh, graphs, and other composited elements.
Every composition includes structured JSON describing its visual layers, composition structure, asset relationships, positioning, and rendering information. With approximately 2,917 hours of content, the collection provides structured scene-level data for visual generation, compositing, multimodal reasoning, scene understanding, retrieval, and model development.
Dataset Preview
Representative previews showing multi-layer visual compositions assembled from independently rendered base footage, interface graphics, overlays, particles, atmospheric effects, flares, bokeh, graphs, and other composited elements.
Preview renders represent complete compositions assembled from independently rendered visual layers.
Key Highlights
- • More than 700,000 structured layered video compositions
- • Approximately 2,917 total hours of visual content
- • Average composition duration of approximately 15 seconds
- • Typically 2–4 independently rendered visual layers per composition
- • Structured JSON describing composition and layer relationships
- • Separate visual elements including base video, HUD graphics, overlays, particles, flares, bokeh, and atmospheric effects
- • Preview renders and production metadata associated with compositions
- • Non-destructive scene structure preserved instead of flattened video alone
Metadata Fields
Example Metadata Record
composition_id: Available per composition
layers: Available in structured JSON
composition_structure: Available in structured JSON
asset_relationships: Available in structured JSON
positioning: Available in structured JSON
rendering_information: Available in structured JSON
preview_reference: Available for corresponding preview render
production_metadata: Available where applicable
Technical Specifications
Dataset Type
Layered Video Composition Dataset
Library Size
700,000+ compositions
Total Duration
Approximately 2,917 hours
Average Composition Duration
Approximately 15 seconds
Typical Layer Count
2–4 visual layers per composition
Metadata Format
Structured JSON
Composition Structure
Multiple independently rendered visual elements assembled into structured scenes
Layer Types
Base video, HUD graphics, overlays, atmospheric effects, flares, particles, bokeh, graphs, and other composited assets
Preview Assets
Rendered composition previews
Asset Relationships
Preserved within structured composition metadata
Positioning Information
Available within composition JSON
Rendering Information
Available within composition JSON
Audio
None
Licensing, Documentation, and Delivery
Wavebreak Media can provide applicable licensing terms, dataset documentation, and structured JSON metadata information for the layered video composition content, with dataset delivery organized around the intended model-development, research, retrieval, or visual-generation workflow. See our Dataset Licensing & Compliance page for more detail.
Need the Full Dataset?
Request access to the JSON Layered Video Compositions Dataset or discuss composition structures, layer types, metadata, licensing, and technical delivery requirements with Wavebreak Media.
