Qwen Image 3.0

Generate one image from a text prompt.

Input

Fields marked * are required. Review the price before generating.

prompt *

Required. The prompt to generate the image. Max 4500 characters.

Resolution

Required. Quality tier for the generated image.

Additional settings

Ratio

Optional. Aspect ratio of the output. Auto follows the first input image, or gives a square when there is no input image.

Number of Images

Optional. How many images to generate, up to 6. Each generated image is billed.

Negative Prompt

Optional. Specify what to exclude from the output.

Prompt Extend

Optional. Rewrites and expands the prompt for better detail, with slightly longer latency. Useful for short prompts.

Prompt Extend Mode

Optional. Direct suits most cases. Agent rewrites more heavily but works only without an input image, otherwise it falls back to direct.

Thinking Mode

Optional. Improves output quality at the cost of longer generation time. Needs Prompt Extend to be true. The price is the same either way.

Seed

Optional. Random seed for reproducibility (0-2147483647).

Price$0.07 / image

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

Describe layout, subject and any requested wording in a clear order.

Read every letter and check alignment, spacing and the placement of objects.

Provide prompt of up to 4,500 characters. This operation accepts n=1; select resolution as 1K or 2K.

Optional ratio and negativePrompt refine the request. Keep seed when comparing attempts; describe all content in text for this operation.