Skip to main content
Create a custom model in one of four categories — style, object, person, or setting — from 1–10 reference images. Once completed, the model can be composed into image generation, Magic Edit, and styled video.

​
Two ways to submit reference images

Both paths require the models.write scope.

​
Always-applied instruction

Each model carries an optional instruction — always-applied guidance (max 8000 characters). Unlike a per-request prompt, it is injected as mandatory (“MUST FOLLOW”) direction into every image and video generation that composes the model, so brand rules (“always a seamless white background”) hold without repeating them on each call. It is distinct from the model’s default_prompt — an AI-generated capability description that is also appended at generation. Set it at creation and edit it any time with PATCH /models/{id}; on read it is returned as user_instruction.

​
Asynchronous pattern

Creation returns 202 Accepted with a model id; poll GET /models/{id}/status until status is completed (or failed). A webhook_url gives you a push callback — see Webhooks. Model creation is free — its estimated_credits is 0 — but it still requires an active organization subscription; an organization with no usable subscription returns 402. See Pricing.