Skip to main content
POST
/
runwayml
/
v1
/
image_to_video
Create a Runway image-to-video task
curl --request POST \
  --url https://api.cometapi.com/runwayml/v1/image_to_video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'X-Runway-Version: <x-runway-version>' \
  --data '
{
  "promptImage": "https://cdn.britannica.com/70/234870-050-D4D024BB/Orange-colored-cat-yawns-displaying-teeth.jpg",
  "model": "gen3a_turbo"
}
'
{
  "id": "3d957031-9a2a-45e2-9dc7-bc8513059c50"
}
Use this endpoint to animate one source image into a Runway video.

​
Before you call it

  • Send the required X-Runway-Version header, for example 2024-11-06
  • Use model: gen3a_turbo
  • Provide a stable HTTPS promptImage
  • Start with duration: 5 and a common ratio such as 1280:720

​
Task flow

1

Submit the image-to-video request

Create the task with a source image and an optional short motion prompt.
2

Store the returned id

Save the task id for later polling.
3

Poll task status

Use Get Task Details. If the first poll returns task_not_exist, wait a few seconds and retry.
Live validation on 2026-03-13 confirmed that a minimal gen3a_turbo request was accepted and returned an id. After a short delay, both official task-details and reverse feed returned the same wrapped queued status for that task.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Headers

​
X-Runway-Version
string
required

Runway version header, for example 2024-11-06.

Body

application/json
​
promptImage
string
default:https://cdn.britannica.com/70/234870-050-D4D024BB/Orange-colored-cat-yawns-displaying-teeth.jpg
required

Source image URL.

​
model
string
default:gen3a_turbo
required

Runway image-to-video model ID. Choose a current model from the Models page.

​
seed
integer

Random seed for reproducible results. Range: 0–999999999.

​
promptText
string

Text prompt describing the desired motion or scene. Maximum 512 characters.

​
watermark
boolean
default:false

Whether to add a watermark to the output video.

​
duration
integer
default:5

Video duration in seconds. Accepted values: 5 or 10.

​
ratio
enum<string>
default:1280:720

Aspect ratio of the output video.

Available options:
1280:720,
720:1280,
1104:832,
832:1104,
960:960,
1584:672,
1280:768,
768:1280

Response

200 - application/json

Task accepted.

​
id
string
required