Skip to main content
POST
/
generation
/
qwen
/
qwen-image-2
Qwen Image 2.0
curl --request POST \
  --url https://open.skills.video/api/v1/generation/qwen/qwen-image-2 \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>"
}
'
{
  "id": "gen_123",
  "status": "IN_QUEUE",
  "input": {
    "prompt": "a cat",
    "aspect_ratio": "1:1",
    "resolution": "1024x1024",
    "n": 1
  },
  "usage": {
    "total": 20,
    "subscription": 20,
    "permanent": 0
  }
}
Qwen Image 2.0 text-to-image model

Authorizations

​
Authorization
string
header
required

API Key for API endpoints

Body

​
prompt
string
required

Text prompt describing the desired image. Supports Chinese and English.

​
image_urls
string<uri>[]

Input images to transform or use as reference (supports up to 4 images).

​
negative_prompt
string
default:""

Content to avoid in the generated image. Max 500 characters.

Maximum string length: 500
​
image_size
enum<string>

The size of the generated image. If not provided, the size of the final input image will be used. Total number of pixels must be between 512x512 and 2048x2048.

Available options:
square_hd,
square,
portrait_4_3,
portrait_16_9,
landscape_4_3,
landscape_16_9
​
aspect_ratio
enum<string>
default:1:1

Aspect ratio for the generated image.

Available options:
1:1,
16:9,
9:16,
4:3,
3:4,
3:2,
2:3
​
enable_prompt_expansion
boolean
default:true

Enable LLM prompt optimization for better results.

​
seed
integer | null

Random seed for reproducibility (0-2147483647).

Required range: 0 <= x <= 2147483647
​
num_images
integer
default:1

Number of images to generate (1-4).

Required range: 1 <= x <= 4
​
output_format
enum<string>
default:png

The format of the generated image.

Available options:
jpeg,
png,
webp
​
n
integer
default:1

Number of results to generate (1-4)

Required range: 1 <= x <= 4

Response

Generation submission accepted

​
id
string
required

Generation id.

​
status
enum<string>
required

Queue status

Available options:
IN_QUEUE,
IN_PROGRESS,
COMPLETED,
FAILED,
CANCELED
​
input
Input · object
required

Normalized input payload for the generation task.

​
usage
object
required

Credit usage breakdown for the request

​
code
string

Machine-readable generation error code. Present when status is FAILED.

​
message
string

Sanitized human-readable failure message. Present when status is FAILED.