An Alibaba video model combining image animation, native audio, and multiple references for consistent subjects.

What does the output look like?

A boy befriends a robot

A boy and a weathered robot share a quiet moment beneath a full moon in Alibaba’s HappyHorse 1.0 announcement.

Alibaba official example: HappyHorse 1.0 announcement

What can Happy Horse do?

Alibaba video generation with native audio, image animation, and multi-reference subject consistency

Inputs
Text, Image
Durations
3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
Aspect ratios
16:9, 9:16, 1:1, 4:3, 3:4
Output options
720p, 1080p
Typical generation time
About 5 minutes
  • References should agree on defining visual traits rather than present conflicting versions of a subject.
  • Test identity consistency before increasing output resolution.

How much does Happy Horse cost?

Base estimate

$0.15–$0.30 USD / second

1.5–3 credits / second

Estimated dollar cost uses the Solo monthly plan at $0.10 USD per credit. Your cost per credit depends on your plan.

Example: a 3-second clip

$0.45–$0.90 USD(4.5–9 credits)

Reference media and video editing may add to this estimate.

Video cost scales with duration. Resolution, sound, reference media, and generation mode can affect the final charge. Check the total shown in Starpop before generating.

How to use Happy Horse

  1. Click “Create with Happy Horse” and sign in or create an account. After setup, Starpop opens a new video workspace tab with the model selected.
  2. Describe the scene and sound, using image guidance or reference images when you need to establish a subject.
  3. Choose the duration, aspect ratio, and resolution supported by the selected input mode.
  4. Review the credit estimate and generate. Check the result in your workspace, then download it or adjust your inputs to try again.