HappyHorse 1.1

Overview

HappyHorse 1.1 is Alibaba's general-purpose video model with three input shapes: text alone, a first-frame still, or multiple reference images that lock look and subject.

Output is 720p or 1080p for about 3-15 seconds across common aspect ratios. When animating a still, framing follows the image and aspect_ratio is ignored. Clips are silent - add soundtrack downstream if needed.

Why choose HappyHorse 1.1

Key strengths

• An upgraded HappyHorse model with stronger motion expression, visual quality, and temporal consistency.
• Improved multi-reference interpretation helps preserve character and product identity across a scene.
• Broad text, image, and reference routes make it suitable for both exploration and controlled production.

Good fit for

• Character-led advertising, ecommerce, short narrative, and social content.
• Complex motion where subject appearance must remain stable.
• Multiple clips built around the same referenced person, product, or style.

Inputs and output settings

This table reflects the model routes and controls currently exposed by MachGen.

Using HappyHorse 1.1

1. Choose a supported generation mode in Playground.
2. Add the required prompt and source or reference assets.
3. Select output settings from the controls shown for that mode.
4. Generate, then inspect the returned asset before reusing the settings through the API.

Practical guidance

• Describe the subject, action or composition, environment, and visual direction in a clear order.
• For image animation, describe the intended motion and camera behavior instead of repeating what is already visible.
• Give each reference a clear role in the prompt, using the names inserted by the Playground.

Modes

• Text to video - prompt alone; aspect_ratio sets the frame.
• Image to video - one still as the first frame; a prompt steers motion; output adopts the image aspect.
• Multi-reference - several images compose look and subject consistency for the scene.

Input limits

• Prompts up to 2,500 characters.
• Images: JPG, PNG, BMP, or WEBP; each side at least 300 px; aspect between 1:2.5 and 2.5:1; up to 10 MB each.
• Duration is an integer from 3 to 15 seconds; default 5.

How to get better HappyHorse 1.1 results

• Use multiple references only when they add complementary views or attributes of the same subject.
• Repeat invariant details such as wardrobe, product geometry, and key colors across related prompts.
• Describe motion in physical terms, including direction, speed, contact, and the camera's response.
• The current MachGen integration returns silent video even though broader official offerings may expose audio.

Limits and availability

• MachGen admits only the modes and settings listed above for this catalog model.
• Source assets must finish uploading before a request can be submitted.
• Generated results can vary between requests, including when the same prompt and settings are reused.
• HappyHorse 1.1 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

Learn more

For model background, technical details, and architecture, see the official Alibaba Cloud HappyHorse 1.1 overview.

Try this model in the MachGen Playground.

Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.

HappyHorse 1.1 pricing

See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.

HappyHorse 1.1 on MachGen

Deployment: Pass-through. HappyHorse 1.1 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

The Playground and API sections on this page list the inputs and output settings exposed for this model.