# Qwen-Image 3.0

> Generate an image from a text prompt, with in-image text rendered natively in 12 languages and legible down to around 10px.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/alibaba/qwen-image/v3.0/text-to-image`
- **Model ID**: `alibaba/qwen-image/v3.0/text-to-image`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: qwen, qwen-image, text-to-image, image-generation, multilingual, text-rendering, typography, poster, infographic

## Pricing

- **Price**: $0.03 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/alibaba/qwen-image/v3.0/text-to-image` 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/alibaba/qwen-image/v3.0/text-to-image/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/alibaba/qwen-image/v3.0/text-to-image/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/alibaba/qwen-image/v3.0/text-to-image/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_):
  Random seed for reproducible results. Omit for a different image each run.
  - Range: `0` to `2147483647`

- **`prompt`** (`string`, _required_):
  What to generate. Long, explicit prompts work best: name each element, where it sits, and the exact wording of any text that should appear in the image (put that wording in quotes). Any language. The ceiling is roughly 4500 tokens, and a longer prompt is rejected rather than trimmed.

- **`watermark`** (`boolean`, _optional_):
  Add a visible watermark to the generated image. Off by default.
  - Default: `false`

- **`image_size`** (`string`, _optional_):
  Output shape and resolution, as an aspect-ratio + resolution preset. 'auto' lets the model choose a shape that suits the prompt. Every size costs the same, so pick the shape the design needs.
  - Default: `"auto"`
  - Options: `"auto"`, `"1_1_1k"`, `"1_1_2k"`, `"4_3_1k"`, `"4_3_2k"`, `"3_4_1k"`, `"3_4_2k"`, `"16_9_1k"`, `"16_9_2k"`, `"9_16_1k"`, `"9_16_2k"`

- **`prompt_extend`** (`boolean`, _optional_):
  Rewrite and expand the prompt before generating. On by default, and it markedly improves short or vague descriptions. Set it to false when you have written a long, precise prompt and want it used as-is.
  - Default: `true`

- **`negative_prompt`** (`string`, _optional_):
  Describe what should be kept out of the image.

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "size": "1024*1024",
  "prompt": "A vintage travel poster for a mountain observatory, three stacked ribbon banners over a night sky illustration of a telescope dome and pine ridge. The top ribbon reads 'STARLIGHT PASS', the middle ribbon reads 'OBSERVATORY TRAIL', and a small caption ribbon at the bottom in neat fine print reads 'Open Nightly - Reserve Ahead'. Bold flat woodcut style, deep indigo and gold palette, every letter crisp and correctly spelled.",
  "watermark": false,
  "prompt_extend": true,
  "negative_prompt": "blurry text, misspelled words, garbled glyphs, extra ribbons, watermark"
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/aQJJaDGqUlb7xzxoZ5rde.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/alibaba/qwen-image/v3.0/text-to-image \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "size": "1024*1024",
  "prompt": "A vintage travel poster for a mountain observatory, three stacked ribbon banners over a night sky illustration of a telescope dome and pine ridge. The top ribbon reads '\''STARLIGHT PASS'\'', the middle ribbon reads '\''OBSERVATORY TRAIL'\'', and a small caption ribbon at the bottom in neat fine print reads '\''Open Nightly - Reserve Ahead'\''. Bold flat woodcut style, deep indigo and gold palette, every letter crisp and correctly spelled.",
  "watermark": false,
  "prompt_extend": true,
  "negative_prompt": "blurry text, misspelled words, garbled glyphs, extra ribbons, watermark"
}')

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("alibaba/qwen-image/v3.0/text-to-image", {
  input: {
  "size": "1024*1024",
  "prompt": "A vintage travel poster for a mountain observatory, three stacked ribbon banners over a night sky illustration of a telescope dome and pine ridge. The top ribbon reads 'STARLIGHT PASS', the middle ribbon reads 'OBSERVATORY TRAIL', and a small caption ribbon at the bottom in neat fine print reads 'Open Nightly - Reserve Ahead'. Bold flat woodcut style, deep indigo and gold palette, every letter crisp and correctly spelled.",
  "watermark": false,
  "prompt_extend": true,
  "negative_prompt": "blurry text, misspelled words, garbled glyphs, extra ribbons, watermark"
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "alibaba/qwen-image/v3.0/text-to-image",
        arguments={
  "size": "1024*1024",
  "prompt": "A vintage travel poster for a mountain observatory, three stacked ribbon banners over a night sky illustration of a telescope dome and pine ridge. The top ribbon reads 'STARLIGHT PASS', the middle ribbon reads 'OBSERVATORY TRAIL', and a small caption ribbon at the bottom in neat fine print reads 'Open Nightly - Reserve Ahead'. Bold flat woodcut style, deep indigo and gold palette, every letter crisp and correctly spelled.",
  "watermark": false,
  "prompt_extend": true,
  "negative_prompt": "blurry text, misspelled words, garbled glyphs, extra ribbons, watermark"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/alibaba/qwen-image/v3.0/text-to-image)
- [OpenAPI Schema](https://modelrunner.ai/models/alibaba/qwen-image/v3.0/text-to-image/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/alibaba/qwen-image/v3.0/text-to-image/llms.txt)