infery
← All models

Qwen Image

qwen/qwen-image

Image generationby Qwen

Qwen Image open source model - fast, highly capable image generation model from Alibaba Qwen

images

Details

Accepts
text + image

Pricing

Price
3.75 cr / image

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedintegerRandom seed. Set for reproducible generation
imagestringInput image for img2img pipeline
promptrequiredstringPrompt for generated image
go_fastbooleanRun faster predictions with additional optimizations.
guidancenumberGuidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
strengthnumberStrength for img2img pipeline
image_sizeenum: optimize_for_quality, optimize_for_speedImage size for the generated image
lora_scalenumberDetermines how strongly the main LoRA should be applied.
aspect_ratioenum: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2Aspect ratio for the generated image
lora_weightsstring
output_formatenum: webp, jpg, pngFormat of the output images
enhance_promptbooleanEnhance the prompt with positive magic.
output_qualityintegerQuality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
negative_promptstringNegative prompt for generated image
extra_lora_scalearrayScales for additional LoRAs as an array of numbers (e.g., 0.5, 0.7). Must match the number of weights in extra_lora_weights.
replicate_weightsstring
extra_lora_weightsarray
num_inference_stepsintegerNumber of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.
disable_safety_checkerbooleanDisable safety checker for generated images.