wan-2.7-image-pro
Wan 2.7 Image Pro is Alibaba's flagship image model — text-to-image **and** image edit in one endpoint, with **4K output** support, optional thinking mode for higher-quality reasoning, and image-set mode for generating coherent variant grids from a single prompt.
Input
Describe the image to generate, or the edit to apply when input images are provided.
Optional reference images (up to 9). Leave empty for text-to-image; pass one or more for editing, style transfer or multi-reference generation.
0 / 9
Output resolution. Use 1K / 2K / 4K to auto-size from the input(s), or pick an explicit WIDTH*HEIGHT pair from the enum.
How many images to generate (1-4 in standard mode, 1-12 in image_set_mode).
Generate a coherent set of related images from one prompt — character expressions, product variants, scene angles.
Enable enhanced reasoning for higher-quality text-to-image output. Slower; recommended for hero shots.
Optional random seed for reproducible generations.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/alibaba/wan-2.7-image-pro \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'