---
title: "Create a Runway image-to-video task"
method: POST
path: "/runwayml/v1/image_to_video"
---

# Create a Runway image-to-video task

`POST /runwayml/v1/image_to_video`

Submit a source image plus optional motion prompt and receive a task id for later polling.

## Headers

- `X-Runway-Version` string, required

## Request body

- object
  - `promptImage` string, required — Source image URL.
  - `seed` integer — Random seed for reproducible results. Range: 0–999999999.
  - `model` string, required — Runway image-to-video model ID. Choose an available model from the [Models page](/overview/models).
  - `promptText` string — Text prompt describing the desired motion or scene. Maximum 512 characters.
  - `watermark` boolean — Whether to add a watermark to the output video.
  - `duration` integer — Video duration in seconds. Runway support is model/version dependent; use 5 or 10 for the broadest compatibility. CometAPI forwards this value to Runway.
  - `ratio` string — Requested output ratio. Accepted values are Runway model/version dependent. With X-Runway-Version 2024-11-06, use a resolution-style value accepted by the selected model, such as 1280:768, 768:1280, 1280:720, or 720:1280. Read these as WxH targets, but completed media may normalize, so inspect the returned file before relying on exact pixels.

## Response `200`

Task accepted.

- object
  - `id` string, required

---

[API](https://skmtc.net/cometapi/apis/create-api-key.md) · [All operations](https://skmtc.net/cometapi/apis/create-api-key/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/cometapi/create-api-key/versions/0863102dbf34/schema)