Skip to main content

Overview

Image-to-video models animate a reference image based on a text prompt. The output video preserves the subject and composition of the input image while adding motion.

Which models support this?

Check the id field from GET /v1/models — image-to-video models contain image-to-video in their ID:

Requirements

  • The image field is required for these models
  • The URL must be publicly accessible (not behind auth, not a presigned URL that expires)
  • Supported formats: JPEG, PNG, WebP

Example

Submitting an image-to-video model without an image field will return HTTP 400.