> ## 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.

# Image Edits

> OpenAI-compatible POST /v1/images/edits

## Introduction

`POST /v1/images/edits` is the OpenAI-compatible image editing endpoint. Supported models include:

* **Qwen**: `qwen-image-edit-plus` — see [Qwen Image](/en/api-reference/endpoint/qwen-image)
* **GPT-Image-2**: JSON or `multipart/form-data`

Text-to-image uses `POST /v1/images/generations`. GPT-Image-2 can also use generations with an `image` field — see [GPT-Image-2](/en/api-reference/endpoint/gpt-image-2).

## Authentication

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

## Request examples

<Tabs>
  <Tab title="GPT-Image-2 (JSON)">
    ```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": "gpt-image-2",
        "prompt": "Change background to beach sunset",
        "image": "https://example.com/photo.png",
        "size": "1024x1024",
        "quality": "high"
      }'
    ```
  </Tab>

  <Tab title="GPT-Image-2 (multipart)">
    ```bash theme={null}
    curl -X POST "https://api.gravitex.ai/v1/images/edits" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -F "model=gpt-image-2" \
      -F "prompt=Change background to beach sunset" \
      -F "image[]=@photo.png"
    ```
  </Tab>

  <Tab title="Qwen">
    ```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/input.webp"},
              {"text": "Change scene to winter snow"}
            ]
          }]
        }
      }'
    ```
  </Tab>
</Tabs>

See [Image generation](/en/api-reference/endpoint/image-generation) for model-specific details.