Video Gen Editor

HappyHorse 1.1: Alibaba's AI Video Model for Performances

HappyHorse 1.1 is Alibaba's multimodal video model for text-to-video, image-to-video and reference-to-video. The 1.1 update improved motion continuity, character consistency, skin and facial detail, and shot logic, which makes it a good fit for close-up performances and scenes with more than one character.

Free sign-up · see the cost before you generate

HappyHorse 1.1 specs

Made by
Alibaba
Clip length
3 to 15 seconds
Resolutions
720p, 1080p
Shapes
16:9, 9:16, 1:1, 4:3, 3:4
Starts from
Text, Image
Extra inputs
A first frame, up to 9 reference images
Sound
No native audio

HappyHorse 1.1 pricing

HappyHorse 1.1 price per resolution
ResolutionPer second5-second clip10-second clip
720p$0.14$0.70$1.40
1080p$0.18$0.90$1.80

These are the published per-second rates. The composer shows the exact estimate for your settings before you generate, and failed generations aren't charged. Prices last checked September 24, 2026. Credits come with our plans.

What it's good at

  • Up to 9 reference images for characters, outfits and props.
  • 720p and 1080p, in five shapes: 16:9, 9:16, 1:1, about 4:3 and about 3:4.
  • Clips of 3 to 15 seconds.
  • Cinematic shot logic and multi-character scenes.
  • Detailed facial texture in close-ups.

Best for

  • Close-up performances

    Faces, expressions and dialogue moments.

  • Multi-character scenes

    Two or three people interacting in one shot.

  • Reference-driven series

    The same cast across several clips.

  • Story shots

    Scenes for a short film or a text to video script.

Things to know

  • Text-to-video needs an exact size. With a first frame, use a resolution preset instead.
  • A first frame is the only frame option (no last frame).
  • It tops out at 1080p.

A HappyHorse 1.1 prompt to try

Two old friends sit across a kitchen table, one slides a faded photograph across, the other picks it up and smiles slowly; soft afternoon light, shallow depth of field, close-ups.

Add a reference image for each person so both stay recognisable.

Alternatives to HappyHorse 1.1

Compare every AI video model

Use HappyHorse 1.1 for

Frequently asked questions

What is HappyHorse 1.1 best at?

Close-up performances and scenes with several characters, where faces need to look right and stay consistent.

How much does HappyHorse 1.1 cost?

$0.14 a second at 720p and $0.18 at 1080p, so a 5-second 1080p clip is about $0.90.