Wan Image Edit
Calls Ali wan2.7-image-pro to perform image editing.
The public calling convention keeps top-level model, input, response_format, and exposes size, n, watermark, negative_prompt, seed, bbox_list as top-level fields. Input images are placed in input.messages[0].content[].image, and the editing instruction is in a text item within the same array. The request body does not accept a top-level parameters field.
Authorizations
Pass Authorization: Bearer <token> in the request header.
Body
Image editing model name.
wan2.7-image-pro Unified response format.
url, b64_json Output image resolution. For image editing, official specifications such as 1K or 2K are recommended. The gateway maps this to upstream parameters.size.
Number of images to generate. The gateway maps this to upstream parameters.n.
1 <= x <= 4Whether to add a watermark. The gateway maps this to upstream parameters.watermark.
Negative prompt. The gateway maps this to upstream parameters.negative_prompt.
Random seed, range [0, 2147483647]. The gateway maps this to upstream parameters.seed.
0 <= x <= 2147483647Interactive editing bounding box regions, corresponding to input images in order. The gateway maps this to upstream parameters.bbox_list.