qwen-image-edit

This documentation is valid for the following list of our models:

• alibaba/qwen-image-edit

Try in Playground

Model Overview

The image editing variant of our 20B qwen-image model. It expands the model’s distinctive text rendering abilities to editing tasks, making accurate text modifications within images possible.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post

Body

application/json

modelstring · enumRequiredPossible values:

promptstring · max: 800Required

The text prompt describing the content, style, or composition of the image to be generated.

imagestringRequired

The image to be edited. Enter the Base64 encoding of the picture or an accessible URL. Image URL: Make sure that the image URL is accessible. Base64-encoded content: The format must be in lowercase.

negative_promptstring · max: 500Optional

The description of elements to avoid in the generated image.

watermarkbooleanOptional

Add an invisible watermark to the generated images.

Default: false

Responses

200Success

application/json

post

/v1/images/generations

cURLJavaScriptPython

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/images/edits' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --form "prompt=Add a crown to the T-rex’s head." \
  --form "image=@<YOUR_IMAGE_PATH.png>;type=image/png;filename=<IMAGE_NAME>"

200Success

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png",
      "b64_json": null
    }
  ],
  "meta": {
    "usage": {
      "credits_used": 120000
    }
  }
}

Quick Example

Let's generate an image using an input image and a prompt that defines how it should be edited.

Python

import requests
import json  # for getting a structured output with indentation

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
            "model": "alibaba/qwen-image-edit",
            "prompt": "Make the dinosaur sit on a lounge chair with its back to the camera, looking toward the water. The setting sun has almost disappeared below the horizon.",
            "image": "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/t-rex.png"
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))

if __name__ == "__main__":
    main()

JS

Response

{
  "created": 1756832341,
  "data": [
    {
      "url": "https://dashscope-result-sgp.oss-ap-southeast-1.aliyuncs.com/7d/06/20250903/1955eee6/ac748d89-d6b1-4d4e-bc65-eea543098bb9-1.png?Expires=1757438140&OSSAccessKeyId=LTAI5tRcsWJEymQaTsKbKqGf&Signature=aDhUphXV84V1nPMmdRl49ShSKxY%3D"
    }
  ]
}

We obtained the following 1184x896 image by running this code example:

'Make the dinosaur sit on a lounge chair with its back to the camera, looking toward the water. The setting sun has almost disappeared below the horizon.'