# Ideogram Character

> Generate new images of the same character from one reference photo and a text prompt, keeping facial features and distinctive traits consistent across scenes.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/ideogram/character`
- **Model ID**: `ideogram/character`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: ideogram, character, image-to-image

## Pricing

- **Price**: $0.15 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/ideogram/character` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/ideogram/character/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/ideogram/character/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/ideogram/character/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer`, _optional_):
  The same seed and the same prompt given to the same version of the model will output the same image every time.

- **`style`** (`StyleEnum`, _optional_):
  The style type to generate with. AUTO lets the model choose, REALISTIC biases toward photographic results, FICTION toward stylized/illustrative results. Cannot be used with style_codes.
  - Default: `"AUTO"`
  - Options: `"AUTO"`, `"REALISTIC"`, `"FICTION"`

- **`prompt`** (`string`, _required_):
  The text prompt describing the image to generate. The character's identity comes from the reference image; describe the scene, pose, wardrobe, and style here. Put any words you want rendered inside the image in quotes.

- **`image_size`** (`ImageSize | ImageSizeEnum`, _optional_):
  The size of the generated image. Use a preset string (e.g. 'landscape_16_9') or a custom {width, height} object.
  - Default: `"square_hd"`
  - Options: `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`

- **`image_urls`** (`array<string>`, _optional_):
  Optional style reference images (distinct from the character references). Cannot be used together with style_codes.

- **`style_codes`** (`array<string>`, _optional_):
  Optional 8-character hex style codes. Cannot be used together with style or style reference images.

- **`expand_prompt`** (`boolean`, _optional_):
  If true, automatically enriches the prompt with extra descriptive detail before generation (Magic Prompt). Set false to use your prompt exactly as written.
  - Default: `true`

- **`negative_prompt`** (`string`, _optional_):
  A description of what you do NOT want in the generated image.
  - Default: `""`

- **`rendering_speed`** (`RenderingSpeedEnum`, _optional_):
  The speed/quality/cost tradeoff. TURBO is fastest and cheapest, BALANCED is the default, QUALITY is best but slowest and most expensive. Affects both speed and cost.
  - Default: `"BALANCED"`
  - Options: `"TURBO"`, `"BALANCED"`, `"QUALITY"`

- **`reference_mask_urls`** (`array<string>`, _optional_):
  Optional masks for the character reference images, restricting which regions are used as references.

- **`reference_image_urls`** (`array<string>`, _required_):
  A set of images to use as character references. Currently only the first image is used; the rest are ignored (maximum total size 10MB). JPEG, PNG, or WebP.

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "style": "AUTO",
  "prompt": "The same man reimagined as a friendly neighborhood barista standing behind a rustic wooden coffee-shop counter, warm morning light through the window, holding a ceramic cup, candid lifestyle photo",
  "image_size": "square_hd",
  "expand_prompt": true,
  "negative_prompt": "",
  "rendering_speed": "BALANCED",
  "reference_image_urls": [
    "https://media.modelrunner.ai/FYKMceHwpZ2cR52xlL2gx.png"
  ]
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/daaia2T4XznhgTmP5bnKz.png"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/ideogram/character \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "style": "AUTO",
  "prompt": "The same man reimagined as a friendly neighborhood barista standing behind a rustic wooden coffee-shop counter, warm morning light through the window, holding a ceramic cup, candid lifestyle photo",
  "image_size": "square_hd",
  "expand_prompt": true,
  "negative_prompt": "",
  "rendering_speed": "BALANCED",
  "reference_image_urls": [
    "https://media.modelrunner.ai/FYKMceHwpZ2cR52xlL2gx.png"
  ]
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("ideogram/character", {
  input: {
  "style": "AUTO",
  "prompt": "The same man reimagined as a friendly neighborhood barista standing behind a rustic wooden coffee-shop counter, warm morning light through the window, holding a ceramic cup, candid lifestyle photo",
  "image_size": "square_hd",
  "expand_prompt": true,
  "negative_prompt": "",
  "rendering_speed": "BALANCED",
  "reference_image_urls": [
    "https://media.modelrunner.ai/FYKMceHwpZ2cR52xlL2gx.png"
  ]
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "ideogram/character",
        arguments={
  "style": "AUTO",
  "prompt": "The same man reimagined as a friendly neighborhood barista standing behind a rustic wooden coffee-shop counter, warm morning light through the window, holding a ceramic cup, candid lifestyle photo",
  "image_size": "square_hd",
  "expand_prompt": true,
  "negative_prompt": "",
  "rendering_speed": "BALANCED",
  "reference_image_urls": [
    "https://media.modelrunner.ai/FYKMceHwpZ2cR52xlL2gx.png"
  ]
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/ideogram/character)
- [OpenAPI Schema](https://modelrunner.ai/models/ideogram/character/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/ideogram/character/llms.txt)