video/motion-transfer

Motion-transfer pipeline — animate a persona using a reference video’s motion.

Category: video
Source: workflows/video/motion_transfer.py

Input Schema

Field	Type	Default	Description
`driving_video_url`	`object`	—
`motion_model`	`string`	`"fal-ai/live-portrait"`
`persona_gallery_id`	`object`	—
`persona_index`	`integer`	`0`
`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.
`source_image_url`	`object`	—
`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

No schema defined.

Task Pipeline

resolve_inputs → transfer_motion → upload_result

Task	Description
`resolve_inputs`	Validate and resolve motion-transfer inputs.
`transfer_motion`	Execute motion transfer via FAL or Seedance.
`upload_result`	Upload motion-transfer result as a Fabric asset.

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: video/motion-transfer

# Optional fields — copy any line(s) under `input:` and uncomment to set:
#   driving_video_url: null
#
#   motion_model: fal-ai/live-portrait
#
#   persona_gallery_id: null
#
#   persona_index: 0
#
#   source_image_url: null
#

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=video/motion-transfer' \
  -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.).

Warnings

Last user task upload_result has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.
Task transfer_motion has no Pydantic types — contract is opaque to consumers.