Skip to main content
POST
/
generate
/
image
/
qwen
/
2512
Qwen 2512
curl --request POST \
  --url https://api.krea.ai/generate/image/qwen/2512 \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "Cybernetic skyline with flying cars and holograms, reflecting a futuristic anime realm."
}
'
{
  "job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "backlogged",
  "created_at": "2023-11-07T05:31:56Z",
  "completed_at": null,
  "result": null
}

Authorizations

​
Authorization
string
header
required

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

Headers

​
X-Webhook-URL
string<uri>

URL to receive a POST request when the job completes. The webhook will receive the job data including results.

Body

application/json
​
prompt
string
required
​
negative_prompt
string
default:""
​
width
integer
default:1024
​
height
integer
default:1024
​
num_inference_steps
integer
default:30
​
cfg_scale
number
default:4
​
seed
string
​
batchSize
integer
default:1
Required range: 1 <= x <= 4
​
skipPromptExpansion
boolean
​
styles
object[]

Styles (typically LoRAs) to use for the generation.

Note: The style must be public, trained by this API user, or shared with your workspace. Styles trained in the Krea app are owned by your user account — to use them via the API, first share them with your workspace via the app UI or POST /styles/{id}/share/workspace.

Response

The resulting job data. This will be returned in a pending state until the job is completed. See /jobs/{id} for retrieving the results.

​
job_id
string<uuid>
required
​
status
enum<string>
required
Available options:
backlogged,
queued,
scheduled,
processing,
sampling,
intermediate-complete,
completed,
failed,
cancelled
​
created_at
string<date-time>
required
​
completed_at
null
required
​
result
null
required