Presets and workflows

A preset turns one file into one short video. A workflow template chains several steps into a whole ad.

Presets

Pick a template and add one file. The preset writes the prompt, the scene and the motion, so there is no prompt to write.

Preset	What you get	You bring	Length	Sound	Takes per run
Show Your App	Your app screenshot on a real person's phone, animated. Vertical	A template, one app screenshot	Always 5 s	None	1 to 4
Fashion Try On	Your clothes on a template model, animated. Vertical	A template, one photo of the clothes	5 or 10 s (5 by default)	Optional	1 to 4

Each take comes back as its own video, grouped with the others: Variants.

Run a preset

List the templates (which tool or route) and keep the template_id (captpl_) the person picks. Read it fresh each time.
Upload the file and keep its ast_ id: Bring your own files.
Estimate, then submit with config.template_id and the file in reference_images: Price first.

Estimate body: Fashion Try On, 10 seconds

{
  "capability_id": "preset_fashion_tryon",
  "config": {
    "template_id": "captpl_0193c8f0a1b24e7f9d3c5a6b7e8f00b2",
    "reference_images": [
      {
        "assetId": "ast_0193c8f0a1b24e7f9d3c5a6b7e8f0012",
        "alias": "image1",
        "role": "reference"
      }
    ],
    "duration": 10,
    "generate_audio": false
  }
}

Fashion Try On takes duration (5 or 10) and an optional generate_audio.
Show Your App takes the same body without those two fields.

Preset fields and refusals: Capabilities API.

Workflow templates

A workflow template is a ready-made chain of steps: writers, images, video and captions. One call runs them all. Your plan decides which templates you can run.

Template	What you get	You bring
Creator to camera	An invented creator talks to camera about your brand	Brand text, a voice
Product photo to spoken ad	A creator holds your product and says your line	Brand text, product photo
Two directions, both shot	Two ad concepts, each a vertical clip	Direction text, product photo
Make a finished ad move	Your ad animated in and out, as two clips	One finished ad image
Four hooks, four creatives	Four statics, each with its own opening line	Brief, packshot, an ad whose look you like
Rebuild an ad around your product	Two static remakes of a working ad, with your product	The ad to clone, product photo, direction text
Six angles from one photo	Six new camera angles	One photo of your model
One creative, every placement	Your ad rebuilt for 1:1, 4:3, 9:16 and 21:9	Your ad
Reframe for feed and story	Your creative laid out in four shapes	Your creative
Your app screen, in the world	Someone holding a phone with your screen on it	Scene text, app screen
App review from a creator	An invented creator talks about your app	Brief, app screenshot, a voice
Two stills, one camera move	One clip from the first frame to the last	Start frame, end frame, camera move text
Your product on the street	Billboard, metro and bus shots, then filmed	Brand text, product photo
Your product as a character	A talking 3D cartoon ad, stitched and captioned	Brief, product photo, two style images
Results across thirty days	Four vertical statics, day 1 to day 30	Brief, packshot, brand board
Four takes, one long ad	One creator, four shots, cut into one ad	Creator look, brief, product photo, a line and a voice per shot

The text boxes hold example copy about an invented product. Replace it with your brand facts, written out: the AI Writer steps cannot open a link.
A talking actor step takes its face from an earlier step and runs the two steps itself. Set only its voice (a voc_ id) and leave the actor empty, or the face is replaced.
Pick a matching voice. Creator to camera needs a voice on its video step. Pick one that fits the Creator: line in its brand text.

Templates that need files

Only Creator to camera runs from words alone. A run cannot carry files, so for any other template, add them in the app first:

Open the template in the app and drop the files into its upload cards.
Click Open in Agent in the workflow's top bar, then Copy prompt. The prompt carries the saved workflow's id.
Paste it to your agent. It runs that saved workflow, files included.

The first time an agent runs a template, it makes a copy in your workspace named <template name> (agent). Later runs reuse that copy, so files you add to it stay.

Run a workflow

List the templates, start a run, then read the run until it ends.

Tool calls

1. list_templates     no arguments
2. run_workflow       the arguments below
3. get_workflow_run   workflow_run_id, again until still_running is false

run_workflow arguments

{
  "template_key": "ugc_face_cam",
  "max_credits": 1500,
  "inputs": [
    {
      "node": "f_brand",
      "field": "text",
      "value": "Brand: Northpeak trail socks. ... Creator: a man in his thirties."
    },
    {
      "node": "f_video",
      "field": "voice",
      "value": "voc_0193c8f0a1b24e7f9d3c5a6b7e8f0099"
    }
  ]
}

get_workflow_run arguments

{
  "workflow_run_id": "wfr_..."
}

Send template_key or workflow_id, never both.

The start answers with a workflow_run_id (wfr_), not a finished ad. Names can change, so match templates on template_key.

Rules for every run

max_credits covers every step, not one. There is no estimate for a whole run.
Too low and the whole run is refused with max_credits_exceeded. limit.required_credits says what it needs, and nothing is charged.
Workspace limits apply: the per-generation limit to each step, the daily budgets to the whole run. See Spend limits.
One run per workflow at a time. A second start gets submission_in_flight (409).
Inputs set text, settings, actors and voices for this run only, never files or the number of takes. One bad input refuses the whole run.
Read the run about every 30 seconds until still_running is false. Files are in nodes[].generations[].outputs[]: Download links.
Agents cannot build, edit, stop or retry a workflow: do that in the app. On partial or failed, read each step's error, fix the input and start a new run.

Every field, status and error: Workflows API.