{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"revised_prompt": "<string>"
}
],
"metadata": {}
}Call Ali wan2.7-image-pro for text-to-image generation.
The public contract keeps top-level model, input, and response_format, while exposing size, n, watermark, thinking_mode, enable_sequential, color_palette, and seed as top-level fields. The prompt is provided in input.messages[0].content[0].text. Top-level parameters is not accepted.
{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"revised_prompt": "<string>"
}
],
"metadata": {}
}Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Text-to-image model name.
wan2.7-image-pro Show child attributes
Unified response format.
url, b64_json Output image resolution, such as 1K, 2K, 4K, or explicit width and height pixels. The gateway maps it to upstream parameters.size.
Number of output images. The range is 1-4 when sequential mode is disabled, and 1-12 when sequential mode is enabled. The gateway maps it to upstream parameters.n.
1 <= x <= 12Whether to add watermark. Explicit false is preserved and mapped to upstream parameters.watermark.
Whether to enable thinking mode. The gateway maps it to upstream parameters.thinking_mode.
Whether to enable sequential multi-image mode. The gateway maps it to upstream parameters.enable_sequential.
Custom color palette. The gateway maps it to upstream parameters.color_palette.
Show child attributes
Random seed. Explicit 0 is preserved and mapped to upstream parameters.seed.