Presets

A preset is a saved set of scene and styling instructions that you can reuse across jobs. Instead of rebuilding the same configuration every time, save it once and reference it by preset_code.

Presets are typed: each preset targets a specific kind of job, and the platform validates that the preset's instructions match the job you use it with.

Preset types

Type	Used with
`model_swap`	Model Swap jobs
`flat_2_model`	Flat Lay on Model jobs
`identity_creation`	Identity generation jobs
`create_packshot`	Packshot creation jobs

Key fields

Field	Description
`preset_code`	Stable identifier you should store in your integration
`name`	Human-readable label, unique per user
`description`	Optional free-form description
`type`	One of the preset types above
`instruction_data`	JSON object holding the scene and styling instructions
`visibility`	`private`, `shared`, or `system`
`categories`	Categories the preset belongs to
`created_at`	Creation datetime (UTC, ISO 8601)
`updated_at`	Last update datetime (UTC, ISO 8601)

Creating presets

There are three ways to create a preset.

Manually

Provide a name, a type, and the instruction_data object directly. Use this when you already know the exact instructions you want to reuse.

From a reference image

Upload an image and the platform extracts a matching instruction_data payload using AI. The response also includes a suggested name and description so you can save the preset in one step.

This is useful when you have a target look or scene in mind and want to recreate it consistently across future jobs.

From a text description

Provide a natural-language description of the scene or styling you want, and the platform generates a matching instruction_data payload.

Preset extraction from images or text consumes credits. See Credits for details.

Account limits

Non-enterprise accounts have a maximum number of presets. If you reach the cap, the create endpoint returns 429. Delete unused presets or contact us to raise the limit.