Alibaba

HappyHorse 1.1

Name: HappyHorse 1.1
Author: Alibaba

HappyHorse 1.1 is the current generation of Alibaba's HappyHorse AI video model family, served through Alibaba Cloud Model Studio (Bailian). It generates up to 15 seconds of video at 720p or 1080p from a text prompt or a first-frame image, across five aspect ratios.

HappyHorse 1.1 supports Text-to-Video (T2V) and first-frame Image-to-Video (I2V): generate a clip directly from a prompt, or upload a still image and have the model animate it into motion. Clips run from 3 to 15 seconds at 720p or 1080p, with 16:9, 9:16, 1:1, 4:3 and 3:4 aspect ratios for text-to-video (image-to-video infers the frame from your still). On Astorie, HappyHorse 1.1 runs as one node on the infinite canvas — wire an image node into it for first-frame animation, fan a prompt out to multiple video models side by side, and keep every take in the version tray.

Try HappyHorse 1.1 Free

Illustrative sample of a HappyHorse still showing a multi-shot 1080p scene with an expressive character on the Astorie canvas — Illustrative sample — representative output, not a verbatim model render

Capabilities

Text-to-Video

Image-to-Video

Video-to-Video

Reference Images

End Frame

Storyboard

Audio-Driven

Supported Aspect Ratios

16:99:161:14:33:4

Best For

Video generation up to 15 seconds — longer than most models' default clip length
First-frame I2V workflows that animate a hero still into a finished clip
Vertical, square and classic formats: five aspect ratios for text-to-video
Cost-controlled drafts at 720p with a 1080p final pass
Chinese-language prompting alongside English

Strengths

Up to 15 seconds per generation at 1080p
Both text-to-video and first-frame image-to-video in one model
Five aspect ratios for text-to-video, including vertical 9:16
Long prompt budget for detailed scene direction

Limitations

Prompts are capped at 5,000 non-Chinese characters or 2,500 CJK characters
Reference images for I2V must be 10 MB or smaller
On Astorie today, text-to-video and first-frame image-to-video are the exposed modes
Single quality tier — no Standard/Pro split inside the model

Tips & Best Practices

Use the long prompt budget: spell out subject, camera movement, lighting and pacing for more controlled shots.

For first-frame I2V, upload a clean hero still under 10 MB; the model animates it into the finished clip.

Pick the aspect ratio to match the destination — 9:16 for shorts and feeds, 16:9 for widescreen cuts.

Use HappyHorse 1.1 on Astorie

Connect HappyHorse 1.1 with other AI models on Astorie's infinite canvas. No GPU required — start free.

Get Started Free