Qwen3 Text to Image

Qwen3 Text to Image OpenAPI Specification

By felipederosilva·Created 24 days ago·Updated about 11 hours ago· 0

Qwen3 Text to Image

◄promptA futuristic city at sunset, cinematic lighting, ultra detailed.►

◄resolution1K►

◄image_size1:1►

◄output_formatpng►

◄prompt_extendtrue►

◄nsfw_checkerfalse►

◄negative_promptblurry, low quality, distorted►

◄seed1►

◄timeout_seconds1200►

◄callback_url►

CategoryKIE Next/Image/Qwen

Inputs (10)

Name	Type	Default	Description
prompt	STRING	A futuristic city at sunset, cinematic lighting, ultra detailed.	The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported.
resolutionopt	COMBO	1K	The output image resolution.
image_sizeopt	COMBO	1:1	The output image size.
output_formatopt	COMBO	png	The generated image format.
prompt_extendopt	BOOLEAN	true	Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions.
nsfw_checkeropt	BOOLEAN	false	Whether to enable content filtering. Optional. Defaults to false. When set to false, content filtering is disabled and all results are returned directly by the model. Note: Content filtering cannot guarantee that all inappropriate content will be detected. If the filtering results do not meet your requirements, you must implement additional content moderation measures.
negative_promptopt	STRING	blurry, low quality, distorted	The negative prompt that describes content you do not want to appear in the image.
seedopt	INT	10–2147483647	The random seed. Value range: [0, 2147483647]. A fixed seed helps maintain relatively stable results.
timeout_secondsopt	INT	120030–7200	—
callback_urlopt	STRING		Optional KIE callback URL. Leave empty for normal ComfyUI use.