benchmarks/video-quality

Video generation quality benchmark — compare local vs remote models.

Category: benchmarks
Source: workflows/benchmarks/video_quality.py

Input Schema

Field	Type	Default	Description
aspect_ratio	string	"16:9"	Output aspect ratio.
duration_secs	integer	4	Target video duration in seconds.
models	string[]	[]	Subset of models to benchmark. Empty = all available.
prompt	string	"A golden retriever running through a sunlit meadow, slow motion, cinematic"	Text prompt for video generation.
regenerate	object	—	When set, this run is a regeneration. Workflows may read direction / keep / extra_instructions to modulate prompts; the engine persists parent_run_id and parent_variant_index as run lineage columns.
variants	integer	1	Number of independent variant executions (1–10). When > 1, the engine runs the workflow N times with different sampling, producing N outputs.

Output Schema

Field	Type	Default	Description
kind	object	—	Variant card shape: video / carousel / image / text. Surfaced on the per-variant entry of the run-output API and used by gallery UIs to pick the right layout.
output_dir	string	""
results	object[]	—
summary	object	—

Task Pipeline

benchmark_video_models

Task	Description
benchmark_video_models	Generate video with each model and collect results.

Run-spec example

Save the YAML below as my-run.yaml, edit the values, and run with the CLI or POST it to the API. Required fields are uncommented; optional knobs are documented above the input: block — copy any line under input: and uncomment to set.

workflow: benchmarks/video-quality

# Optional fields — copy any line(s) under `input:` and uncomment to set:
# Output aspect ratio.
#   aspect_ratio: "16:9"
#
# Target video duration in seconds.
#   duration_secs: 4
#
# Subset of models to benchmark. Empty = all available.
#   models: []
#
# Text prompt for video generation.
#   prompt: "A golden retriever running through a sunlit meadow, slow motion, cinematic"
#

input: {}

Run it locally:

fab-workflow --from-file my-run.yaml

Or submit over the wire — the same file is the request body:

curl -X POST 'https://gofabric.dev/v1/workflows/runs?name=benchmarks/video-quality' \
  -H 'Authorization: Bearer fab_xxx' \
  -H 'content-type: application/yaml' \
  --data-binary @my-run.yaml

Every workflow also accepts the universal WorkflowInput fields — variants (1–10 fan-out) and regenerate (creative-direction hints with run lineage). See Run-specs (YAML / TOML / JSON) for the full top-level shape (metadata, priority, bundle, parent, etc.).