---
title: "Generate Image - Tailored Model"
method: POST
path: "/image/generate/tailored"
tags: ["Image Generation"]
---

# Generate Image - Tailored Model

`POST /image/generate/tailored`

**Description**

Generates a new image using a tailored model.

This endpoint translates your input (`prompt` and/or `structured_prompt`) into a structured JSON prompt using the state-of-the-art **Gemini 2.5 Flash** VLM bridge. It internally uses the model's visual schema (backbone) to ensure the generated image matches your trained visual identity.

The response includes both the final `image_url` and the `structured_prompt` (JSON).

**Input Combination Rules**
The request body must include **one** of the following mutually exclusive combinations:
* `prompt`: Generates a new image from text.
* `structured_prompt`: Recreates a previous image exactly (requires seed).
* `structured_prompt` + `prompt`: Refines a previous image using new text instructions.

## Headers

- `api_token` string, required

## Request body

- object
  - `tailored_model_id` string, required — The ID of the tailored model.
  - `tailored_model_influence` number, float — Controls the strength of the tailored model's influence (0.0 - 1.5).
  - `prompt` string — Text-based instruction for generation or refinement.
  - `structured_prompt` string — A string containing the structured prompt in JSON format for precise recreation/refinement.
  - `negative_prompt` string — Concepts to exclude from the generated image.
  - `guidance_scale` integer — Adherence to the prompt (3-5).
  - `aspect_ratio` '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '4:5' | '5:4' | '9:16' | '16:9'
  - `steps_num` integer
  - `seed` integer — Seed for deterministic generation.
  - `sync` boolean — If false, returns a 202 and status URL. If true, returns 200 with result.
  - `prompt_content_moderation` boolean
  - `visual_output_content_moderation` boolean

## Response `200`

Successful operation (Synchronous).

- object
  - `image_url` string
  - `structured_prompt` string

## Other responses

- `202` — Accepted (Asynchronous).
- `400` — Bad request. Invalid parameters.
- `403` — Forbidden. Model does not belong to organization.
- `422` — Unprocessable Entity (Moderation failure).
- `429` — Request limit exceeded.
- `500` — Internal Server Error.

---

[API](https://skmtc.net/bria-ai/apis/tailored-generation-api-reference.md) · [All operations](https://skmtc.net/bria-ai/apis/tailored-generation-api-reference/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/bria-ai/tailored-generation-api-reference/revisions/806c6d31631b/schema)