Presets and workflows
Ready-made recipes: presets for one file, workflow templates for a whole ad.
Read as MarkdownA 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_idand the file inreference_images: Price first.
{
"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 optionalgenerate_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, captioned, with music, in 9:16 and 4:5 | Brand text |
| Four openings, one ad | Four finished ads: one body behind four different openings, for A/B tests | Brand text |
| Product photo to spoken ad | A creator holds your product and talks, then a close-up, with music and captions | Brand text, product photo |
| Two people: podcast, interview or skit | Two invented people in one scripted scene, captioned, with music | Brand text |
| Long-form sales video | About a minute of one creator selling your offer, with a cutaway, captions and music | Offer text, a voice (the same one on each take) |
| Studio commercial from one photo | Two short commercials with sound and music, in 9:16 and 16:9 | Brand text, product photo |
| Show it working: unboxing, how-to, before and after | A hands-only, narrated product demo with sound effects, music and captions | Brand text, product photo, a voice |
| Make a finished ad move | Your static ad animated in, held and out, looping, with music, in three shapes | One finished ad image |
| Sale ad in every size | A moving offer ad in launch, midway and last-day versions, in four shapes | Sale text |
| Your product on the street | Three fake out-of-home stunts with your product, plus one cut | Brand and city text, product photo |
| Try-on with a talking hook | A creator hook, then your garment worn by a model, with music and a price card | Brand text, garment photo |
| Four hooks, four creatives | Four statics, each a different hook, in 4:5 and 9:16 | Brand text, product photo |
| Rebuild an ad around your product | A working ad's layout rebuilt with your brand, two versions in 9:16 and 4:5 | The ad to remake, product photo, brand text |
| Store-page photo pack | Six store-page shots of your product, plus a 4:5 crop | Product text, product photo |
| One creative, every placement | Your ad rebuilt (not cropped) for 1:1, 4:5, 9:16 and 16:9 | Your ad |
| App review from a creator | A creator talks up your app or game while your real screen plays on phones | App text, app screenshot, a voice |
| Software explainer with a presenter | A presenter explains your software around your real screenshot, in 16:9 and 9:16 | Software text, screenshot, a voice |
| Tour from photos: homes, stays and venues | A narrated, captioned tour in 9:16 and 16:9 | Listing text, six photos, a voice |
| Local business promo | A hosted promo of your place with your offer, captions and music | Business text, three photos |
| Finish a raw clip | Your clip back with sound effects, music and captions, in 9:16 and 4:5 | One raw clip |
- 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. Leave the actor empty, or the face is replaced.
- The voice is matched to the face. Leave it empty and each new face gets a voice that fits it: a man's voice for a man, a woman's for a woman. Set a voice (a
voc_id) only to use the same one every run. If the face cannot be read, the run uses a default voice and still finishes. - A template with a voice-over step needs one voice. The voice-over cannot follow the face, so set the same voice on it and on each talking step.
Templates that need files
Five templates run from words alone: Creator to camera, Four openings, one ad, Two people: podcast, interview or skit, Long-form sales video and Sale ad in every size. 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.
1. list_templates no arguments
2. run_workflow the arguments below
3. get_workflow_run workflow_run_id, again until still_running is false{
"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"
}
]
}{
"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_creditscovers 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_creditssays 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_runningisfalse. Files are innodes[].generations[].outputs[]: Download links. - Agents cannot build, edit, stop or retry a workflow: do that in the app. On
partialorfailed, read each step's error, fix the input and start a new run.
Every field, status and error: Workflows API.