Wan 2.5 Image Edit

Wan 2.5 Image Edit · Alibaba — Image to image · Up to 3 source images. Call it through one queue API and pay for the options you pick.

modellane/wan-2.5-image-edit · Image to image · Alibaba

Image to image model: up to 3 source images.

Prompt prompt — required Describe what you want produced as concretely as you can.
Negative prompt negative_prompt — optional Things you don't want to see in the output.
Source images images — required, range: 1–3 Images used in the generation; their order can affect the result.
Size size — optional, options: 576*1344, 720*1280, 720*1680, 768*1024, 800*1200, 816*1904, 936*1664, 960*1280, 960*1440, 1024*768, 1024*1024, 1040*1560, 1104*1472, 1200*800, 1280*720, 1280*960, 1280*1280, 1344*576, 1440*960, 1472*1104, 1560*1040, 1664*936, 1680*720, 1904*816 The pixel size of the output.
Prompt expansion enable_prompt_expansion — optional, default: Yes When on, the model expands the prompt with its own rules.
Seed seed — optional, default: Random The same seed and the same settings produce a similar result; leave it empty and one is picked at random.

Output and retention

The generated file and your input are kept for seven days and then deleted.

Submit to the queue: POST /v1/queue/modellane/wan-2.5-image-edit

Status, result, cancellation and error codes work the same for every model; see the API docs.

Everything on this page is public; you need an account to run the model.