Wan 2.7 Image to Video

Wan 2.7 Image to Video · Alibaba — Image to video · 2–15 s · Up to 1080p · End frame. Call it through one queue API and pay for the options you pick.

modellane/wan-2.7-image-to-video · Image to video · Alibaba

Image to video model: 2–15 s, up to 1080p, end frame.

Prompt prompt — optional 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 image image — optional The frame the generation starts from.
Last frame last_image — optional If given, the generation ends on this frame; it can be left empty.
Source video video — optional The video used as the source for the generation.
Source audio audio — optional
Resolution resolution — optional, options: 720p, 1080p The output resolution.
Duration duration — optional, default: 5, range: 2–15 A longer duration raises the price directly.
Extend prompt prompt_extend — optional, default: Yes When on, the prompt is automatically expanded by the model.
Seed seed — optional, default: Random, range: -1–2147483647 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-2.7-image-to-video

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.