Wan 2.5 Text-To-Image Preview generates high-fidelity images from text descriptions. It supports batch generation of up to 4 images per request with flexible resolution and aspect ratio control.
Key Features
Batch generation — Generate 1-4 images per request
Flexible resolution — 768x768 to 1440x1440, aspect ratios from 1:4 to 4:1
Long prompts — Up to 2,000 characters for detailed descriptions
Intelligent prompt rewriting — Optional prompt optimization for better results
Pricing
Per Image $0.03
Parameters
nintegerDefault: 4
Number of images to generate (1-4)
seedinteger
Random seed for reproducibility [0, 2147483647]
sizeEnumDefault: "1280*1280"
Image resolution in format "width\*height" (e.g., "1280\*1280")
Default: 1280\*1280
Total pixels: [768\*768, 1440\*1440], aspect ratio: [1:4, 4:1]
Possible values: 1280*1280, 768*768, 1440*1440
promptstring* required
Text description for the image (max 2000 characters).
prompt_extendbooleanDefault: false
Enable intelligent prompt rewriting (improves short prompts but increases processing time)
safety_filterbooleanDefault: true
Enable content safety filter. Defaults to true. Set to false to disable content safety inspection.