Skip to main content
POST
/
v1
/
images
/
edits
Qwen Image Editing
curl --request POST \
  --url https://api.powertokens.ai/v1/images/edits \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen-image-2.0-pro",
  "prompt": "<string>",
  "n": 1,
  "size": "1024*1024",
  "response_format": "url",
  "seed": 123,
  "watermark": false,
  "prompt_extend": true,
  "negative_prompt": "<string>",
  "extra": {
    "input": {},
    "parameters": {}
  }
}
'
{
  "created": 123,
  "data": [
    {
      "url": "<string>",
      "b64_json": "<string>",
      "revised_prompt": "<string>"
    }
  ],
  "metadata": {}
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

​
model
enum<string>
required

Image editing model name.

Available options:
qwen-image-2.0-pro,
wan2.7-image-pro
​
prompt
string
required

Image editing prompt describing desired effect. Supports Chinese and English, max 800 characters.

​
n
integer
default:1

Number of images to generate. qwen-image-2.0, qwen-image-edit-max/plus series support 1-6, qwen-image-edit supports 1 only.

Required range: 1 <= x <= 6
​
size
string

Output resolution in format width*height. Total pixels between 512512 and 20482048.

Example:

"1024*1024"

​
response_format
enum<string>
default:url

Response format.

Available options:
url,
b64_json
​
seed
integer

Random seed, range [0, 2147483647].

​
watermark
boolean
default:false

Whether to add watermark.

​
prompt_extend
boolean
default:true

Whether to enable prompt intelligent rewriting.

​
negative_prompt
string

Negative prompt.

​
extra
object

Extended parameters containing input and parameters fields.

Response

Success, returns image editing result.

​
created
integer<int64>

Unix timestamp of creation time (seconds).

​
data
object[]

List of generated images.

​
metadata
object

Additional result metadata. Returned fields may vary by capability.