image/generate

AI Image Generation — Gemini native image generation with text.

Category: image
Source: workflows/image/generate.py

Input Schema

Field	Type	Default	Description
hook	string	""	Hook text to distill into overlay
num_thumbnails	integer	3	Number of variants to generate
platform	string	"youtube"	Target platform
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.
thumbnail_style	string	"vibrant, dramatic lighting, cinematic"	Visual style
thumbnail_text	string	""	Explicit overlay text (skips distillation)
topic	string	""	Video title or topic for context
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	string	"image"	Card kind for consumers — always ‘image’.
selected_thumbnail	string	""	Best thumbnail path
thumbnail_paths	string[]	—	Saved thumbnail paths

Task Pipeline

generate_thumbnail

Task	Description
generate_thumbnail	Generate thumbnails — delegates to SDK stage.

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: image/generate

# Optional fields — copy any line(s) under `input:` and uncomment to set:
# Hook text to distill into overlay
#   hook: ""
#
# Number of variants to generate
#   num_thumbnails: 3
#
# Target platform
#   platform: youtube
#
# Visual style
#   thumbnail_style: "vibrant, dramatic lighting, cinematic"
#
# Explicit overlay text (skips distillation)
#   thumbnail_text: ""
#
# Video title or topic for context
#   topic: ""
#

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=image/generate' \
  -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

• Task generate_thumbnail has no Pydantic types — contract is opaque to consumers.