Skip to main content
POST
Qwen-Image 3.0

Headers

Authorization
string

Body

application/json
prompt
string
required

Text prompt describing the image.

Required string length: 1 - 2000
ratio
enum<string>
default:auto

Aspect ratio. Defaults to auto, which lets the model pick the resolution from the prompt. Note: 1:8 and 8:1 are only produced at the 1K tier.

Available options:
auto,
1:1,
16:9,
9:16,
4:3,
3:4,
2:3,
3:2,
1:2,
2:1,
1:4,
4:1,
1:8,
8:1
image_size
enum<string>
default:2K

Output resolution tier, together with ratio it decides the exact pixel size. See the pricing note above — it also decides what you pay.

Available options:
1K,
2K
image_list
object[]

Optional reference images for image editing, [{"url": "https://..."}]. Up to 3 images, each under 10MB. The array order is the order the prompt refers to them in. Each one adds 0.19 tokens.

Required array length: 1 - 3 elements
negative_prompt
string

Optional. Describes what should not appear in the image.

Maximum string length: 2000
seed
integer

Optional. Fixing the seed makes results more reproducible.

Required range: 0 <= x <= 2147483647
prompt_extend_mode
enum<string>
default:direct

Prompt rewriting mode. agent rewrites more thoroughly but is text-to-image only — sending it together with image_list is rejected.

Available options:
direct,
agent
custom_callback_url
string<uri>

Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.

Example:

"https://your-server.com/goenhance/callback"

Response

code
integer
required
msg
string
required
data
object
required