minimaxiH3 Get access
QwenText-to-videoVendor content policy applies

HappyHorse-1.0 Reference-to-video

Generates videos from one to nine reference images and a text prompt, supporting 720P or 1080P output, flexible aspect ratios, and durations from 3 to 15 seconds.

$0.21per secondStarting price at the base resolution and quality tier.
$1.68Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “A race car hurtles past, its vibrant interplay of light and shadow dancing across the night sky, casting a shimmering, fluid glow upon the vehicle's surface. The imagery features a high-velocity motion blur effect—enhanc…”

What it does

HappyHorse-1.0 Reference-to-video, in practice.

Alibaba HappyHorse 1.0 Reference-to-Video creates short video clips from a text prompt and one or more reference images, helping preserve subjects, objects, or visual cues from the supplied images.

  • Reference-guided generation: Use 1 to 9 images to guide the people, objects, style, or scene elements in the output.
  • Prompt-directed motion: Describe how the referenced elements should move, interact, or appear in the final clip.
  • Flexible framing: Supports `16:9`, `9:16`, `1:1`, `4:3`, and `3:4`.
  • Two output resolutions: Generate at `720P` or `1080P`.
  • Creators producing videos that need to keep a character, product, or prop recognizable.
  • Teams building campaign visuals from approved reference material.

Run HappyHorse-1.0 Reference-to-video

from $0.21/sec
resolution
ratio
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
promptText prompt describing the desired video and how the reference images should be used. Maximum length is 2500 characters.
imagesReference image URLs. Provide 1 to 9 images. Supported formats are JPEG, JPG, PNG, BMP, and WEBP. Each image can be up to 10 MB, with the shorter side at least 400 px and at least 40% of the longer side.
resolutionOutput video resolution.720p 1080p
ratioAspect ratio of the generated video.16:9 9:16 1:1 4:3 3:4
durationVideo duration in seconds.default 5
seedRandom seed for video generation. Use -1 for a random seed.default -1

Sample prompt

The prompt behind the sample.

A race car hurtles past, its vibrant interplay of light and shadow dancing across the night sky, casting a shimmering, fluid glow upon the vehicle's surface. The imagery features a high-velocity motion blur effect—enhanced by cinematic lighting and composition—to forge an atmosphere of intense, dramatic tension. The level of detail is exquisitely rich, delivering a visual quality of 4K resolution.
resolution: 1080Pratio: 16:9duration: 5seed: -1

FAQ

Short answers.

How much does HappyHorse-1.0 Reference-to-video cost?

Pricing starts at $0.21 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $1.68. Usage is billed per request from your balance — no subscription.

Does HappyHorse-1.0 Reference-to-video run uncensored here?

No. Qwen applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists HappyHorse-1.0 Reference-to-video for everything else it does well.

What does HappyHorse-1.0 Reference-to-video take as input?

It is a text-to-video model. Generates videos from one to nine reference images and a text prompt, supporting 720P or 1080P output, flexible aspect ratios, and durations from 3 to 15 seconds.

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run HappyHorse-1.0 Reference-to-video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models