> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gravitex.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Qwen Image

> Alibaba Qwen Image text-to-image and editing

## Introduction

Qwen Image models support Chinese-centric text-to-image and multi-image editing via OpenAI-compatible endpoints:

* **Text-to-image**: `POST /v1/images/generations`, model `qwen-image-plus`
* **Image editing**: `POST /v1/images/edits`, model `qwen-image-edit-plus`

See [Image generation](/en/api-reference/endpoint/image-generation) for full parameters.

## Authentication

<ParamField header="Authorization" type="string" required>
  Bearer Token, e.g. `Bearer sk-xxxxxxxxxx`
</ParamField>

## Supported models

| Model ID               | Description                   | Endpoint                 |
| ---------------------- | ----------------------------- | ------------------------ |
| `qwen-image-plus`      | Text-to-image                 | `/v1/images/generations` |
| `qwen-image-edit-plus` | Edit / I2I (1–3 input images) | `/v1/images/edits`       |

## Request examples

<Tabs>
  <Tab title="Text-to-image">
    ```bash theme={null}
    curl -X POST "https://api.gravitex.ai/v1/images/generations" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "qwen-image-plus",
        "input": {
          "messages": [
            {
              "role": "user",
              "content": [{"text": "An elegant Chinese hall with calligraphy scrolls, ink wash style"}]
            }
          ]
        },
        "parameters": {"prompt_extend": true}
      }'
    ```
  </Tab>

  <Tab title="Image editing">
    ```bash theme={null}
    curl -X POST "https://api.gravitex.ai/v1/images/edits" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "qwen-image-edit-plus",
        "input": {
          "messages": [
            {
              "role": "user",
              "content": [
                {"image": "https://example.com/reference.webp"},
                {"text": "Generate an image: red bicycle on a muddy path in a forest"}
              ]
            }
          ]
        },
        "parameters": {"n": 2, "size": "2048*2048"}
      }'
    ```
  </Tab>
</Tabs>

## Common parameters

* **input.messages**: Qwen message format with `text` / `image` in `content`
* **parameters.n**: Output count; `qwen-image-edit-plus` supports 1–6
* **response\_format**: `url` or `b64_json`

See [Image generation](/en/api-reference/endpoint/image-generation) and [Image edits](/en/api-reference/endpoint/image-edits).