Skip to main content
POST
After submission, a task_id is returned. You can retrieve the result through the unified Query Task Status endpoint or provide a callback_url to receive a completion notification.

Qwen Image 3 Generation

Qwen Image 3 supports text-to-image and multi-reference image generation for posters, product visuals, typography, and natural-language image editing.

Available Models

  • qwen-image-3 - Standard image generation with 1K and 2K output
  • qwen-image-3-pro - Higher-quality image generation with 1K and 2K output
Both models use a unified endpoint. Omit image_urls for text-to-image generation, or provide 1–3 reference images for image-to-image generation.

Parameters

  • prompt is required and supports up to 5,000 characters.
  • size supports 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, and 21:9.
  • resolution supports 1K and 2K.
  • output_format supports png and jpeg.
  • prompt_extend controls automatic prompt enhancement.
  • negative_prompt describes content that should not appear in the output.
  • seed accepts values from 0 to 2,147,483,647.
  • enable_safety_checker controls content safety checking.

Pro Text-to-Image Example

Standard Reference-Image Example

Pro 2K Reference-Image Example

Pro Multi-Reference Example

Authorizations

Authorization
string
header
required

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

Body

application/json
model
enum<string>
required
Available options:
qwen-image-3,
qwen-image-3-pro
input
object
required
callback_url
string<uri>

Response

Task submitted successfully

code
integer
required
Example:

200

data
object
required