infery
← All models

Qwen Image

qwen-image

Image generationby Alibaba
images

Details

Accepts
text + image

Pricing

Price
5.63 cr / image

Prices in credits (1 credit = $0.01).

Data schema

approximate

Input

FieldTypeDescription
nintegerNumber of outputs.
sizestringenum: 1024*1024, 1280*1280, 1440*1440, 1024*1440, 1440*1024, 1080*1920
imagestringInput image (URL or data URI).
promptrequiredstringThe text prompt.
aspect_ratiostringenum: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2
seed The same seed and the same prompt given to the same version of the model will output the same image every time.
lorasarray
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.
use_turbobooleanEnable turbo mode for faster generation with high quality. When enabled, uses optimized settings (10 steps, CFG=1.2).
image_sizeThe size of the generated image.
num_imagesintegerThe number of images to generate.
accelerationstringenum: none, regular, highAcceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text.
output_formatstringenum: jpeg, pngThe format of the generated image.
guidance_scalenumber The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
negative_promptstringThe negative prompt for the generation
num_inference_stepsintegerThe number of inference steps to perform.
enable_safety_checkerbooleanIf set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.
image_urlstringThe URL of the image to edit.
mask_urlstringThe URL of the mask for inpainting
strengthnumberStrength of noising process for inpainting

Output

FieldTypeDescription
imagesarrayGenerated images ([{ url }]).