Skip to main content
HappyHorse 1.1 I2V turns one first-frame image into a 24 fps MP4 video with synchronized audio. The prompt describes the movement and camera behavior that follow the input frame. I2V means image-to-video. This model accepts exactly one image with type: "first_frame".

Key capabilities

  • First-frame image-to-video - Animate a single input image
  • Synchronized audio - Generate audio with the video
  • Resolution - 720P or 1080P
  • Duration - An integer from 3 to 15 seconds
  • Aspect ratio preservation - Output approximately follows the input image ratio

Input image requirements

  • Formats: JPEG, JPG, PNG, or WEBP
  • Input: public HTTP/HTTPS URL or Base64 data URL
  • Dimensions: width and height must both be at least 300 pixels
  • Aspect ratio: from 1:2.5 to 2.5:1
  • File size: up to 20 MB

Quick example

cURL
HappyHorse 1.1 I2V does not accept a ratio setting. The output uses the first-frame image’s aspect ratio as its baseline and may be adjusted slightly for video encoding.

Parameters

API Reference

View the request and response schema.

Task Query

Poll task status and retrieve the result URL.

Official reference

See the Alibaba Cloud Model Studio HappyHorse image-to-video API reference.