Skip to content
Novus Examples
jpg125.9 KB

Street at dusk: scrub-preview sprite sheet

The scrub-preview sheet for the film in this group: 24 tiles in a 6x4 grid, one sampled per second, each 160x90. This is the form a player requests when a viewer drags the scrubber. A two-second clip yields two tiles and proves nothing about tiling; 24 seconds fills the grid.

Preview of Street at dusk: scrub-preview sprite sheet

Specifications

Film
film-street-dusk
Duration Seconds
24
Segments
12
Synthetic
true
Disclosure
AI-generated / synthetic video. Not a recording of a real person, place or event.
Schema Version
1
Tiles
24
Grid
6x4
Tile Width
160
Tile Height
90
Sampled At
1 fps
Alt Text
A 6x4 grid of 24 frames sampled one per second from A slow continuous push down a city street at dusk, shopfronts and passing traffic, wet road reflections, steady camera, one unbroken shot
Alt Text Source
derived

Testing contract

Expected to pass
Scenario
Crop the tile at the offset named by the companion WebVTT index for t=10s.
Expected result
The cue for 10 seconds names x=640, y=90, and the 160x90 rectangle there is the frame at 10 seconds, which is 1.5 seconds into the fifth segment.

What is a .jpg file?

JPG is the common extension for JPEG, a lossy raster format that uses discrete cosine transform compression tuned for photographic images. It is 8-bit truecolor with no alpha channel, and quality is traded against file size via a compression factor. It is ubiquitous for photos on the web and from cameras.

How to use this file

Use an example JPG to test decoders, EXIF/metadata parsers, re-encoding quality, and orientation handling, or to confirm converters and image pipelines process baseline and progressive scans correctly.

How to use this file for testing

“Street at dusk: scrub-preview sprite sheet” is a deterministic Novus Examples fixture for Media handling. Generated stills, clips and audio published in several encodings of identical content, so a media pipeline can be tested on format handling, quality loss and frame or sample extraction against a reference that is known rather than assumed.

Documented properties for this file: JPG · 128,878 bytes. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.

Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such, expect parsers to fail loudly rather than silently accept them.

For image AI or enhancement tools, run the model or filter on this file and diff against the clean or ground-truth companion in the same group when available. Keep seeds and documented damage parameters in your evaluation notes so regressions are attributable.

Code examples

<img src="film-street-dusk-thumbs.jpg" alt="Example image" width="640" loading="lazy">

Generated by generation/comfy_film_wave.py. Free for any use, no attribution required, license.