Skip to main content
POST
/
runwayml
/
v1
/
video_to_video
Generate a video from a video
curl --request POST \
  --url https://api.cometapi.com/runwayml/v1/video_to_video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'X-Runway-Version: <x-runway-version>' \
  --data '
{
  "videoUri": "https://filesystem.site/cdn/20250818/c4gCDVPhiBc6TomRTJ7zNg0KwO1PSJ.mp4",
  "promptText": "string",
  "seed": 4294967295,
  "model": "gen4_aleph",
  "references": [
    {
      "type": "image",
      "uri": "https://cdn.britannica.com/70/234870-050-D4D024BB/Orange-colored-cat-yawns-displaying-teeth.jpg"
    }
  ],
  "ratio": "1280:720",
  "contentModeration": {
    "publicFigureThreshold": "auto"
  }
}
'
{}
Use this endpoint to transform an existing source clip with Runway’s video-to-video workflow. It starts an async task instead of returning the final output immediately.

​
Before you call it

  • Prepare a source video that matches the provider’s input requirements
  • Include the required X-Runway-Version header for the feature set you want
  • Start with one short prompt that describes the change, not a full storyboard

​
Task flow

1

Submit the source clip and prompt

Start the task from this endpoint and save the returned task id.
2

Poll task details

Use Runway to Get Task Details until the task reaches a terminal state.
3

Store the transformed result

Download or persist the finished asset through your normal media pipeline.

​
CometAPI wrapper note

CometAPI keeps Runway’s asynchronous task model and versioned request behavior, but unifies authentication and base URL handling with the rest of the platform.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Headers

​
X-Runway-Version
string
required

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

Body

application/json
​
videoUri
string
default:https://filesystem.site/cdn/20250818/c4gCDVPhiBc6TomRTJ7zNg0KwO1PSJ.mp4
required

HTTPS URL of the source video, or a base64 data URI containing the video.

​
promptText
string
default:A cat yawning in slow motion.
required

Text prompt describing the desired output. Maximum 1000 characters.

​
seed
integer
default:1
required

Random seed for reproducible results. Range: 0–4294967295.

​
model
string
default:gen4_aleph
required

Model variant to use.

​
references
object[]
required

Optional reference images to guide generation. Each item must include type (e.g. image) and uri (HTTPS URL).

​
ratio
string
default:1280:720
required

Aspect ratio of the output video, e.g. 1280:720.

​
contentModeration
object
required

Response

200 - application/json

success

The response is of type object.