Skip to main content
AlibabaMediumHigh

Happy Horse 1.1

Alibaba's Happy Horse 1.1 generates videos from text, animates a single image, or builds a video from multiple reference images. Supports 720p and 1080p, 3-15 second durations, and five aspect ratios.

2090 credits
per 5s 1080p video โ€” billed per second (720p 326/s, 1080p 419/s)
Three modes in one model: text-to-video, image-to-video, reference-to-video
Reference-to-video with up to 9 images โ€” keeps subjects and scenes consistent
720p and 1080p output at 3-15 second durations
Five aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4
Seed support for reproducible generation

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "alibaba/happyhorse-1.1",
  "input": {
    "prompt": "The animal prances across the branch",
    "images": [
      "https://example.com/animal.png"
    ],
    "duration": 5,
    "resolution": "1080p"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringNo-Text prompt (up to 2,500 chars). Optional with a single image; required for text-to-video and reference-to-video. Refer to reference images as [Image 1], [Image 2], etc.
imagesarrayNo[]No images for text-to-video, one image to animate it (image-to-video), or up to 9 for reference-to-video. jpg/png/bmp/webp, โ‰ค10MB each, each side โ‰ฅ300px
resolutionstringNo1080pOutput resolution. 720p bills 210 credits/sec, 1080p bills 270 credits/sec
720p1080p
aspect_ratiostringNo16:9Aspect ratio for text-to-video and reference-to-video. Ignored with a single input image (its ratio is used)
16:99:161:14:33:4
durationintegerNo5Video duration in seconds (3-15). Billed per second of output
3456789101112131415
seedintegerNo-Random seed for reproducible generation (0-2147483647)

How to Provide File Input

There are 3 ways to provide files for the images parameter:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=alibaba/happyhorse-1.1" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:images=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "alibaba/happyhorse-1.1",
  "input": {
    "prompt": "your prompt here",
    "images": ["https://example.com/image.jpg"]
  }
}
See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Image-to-Video Animation

Animate a still image as the first frame of a video

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "alibaba/happyhorse-1.1",
  "input": {
    "prompt": "The animal prances across the branch",
    "images": [
      "https://example.com/animal.png"
    ],
    "duration": 5,
    "resolution": "1080p"
  }
}'

Cinematic Text-to-Video

Generate a video from a text description alone

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "alibaba/happyhorse-1.1",
  "input": {
    "prompt": "A majestic white horse gallops along a black-sand beach at golden hour, mane flowing in the wind, waves crashing in slow motion, cinematic tracking shot",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5
  }
}'

Tips & Best Practices

1Billing is per second of output โ€” iterate at 720p and 5 seconds, then switch to 1080p for the final render
2With multiple reference images, label them in the prompt: 'The character from [Image 1] walks through the scene in [Image 2]'
3A single input image locks the output to that image's aspect ratio โ€” crop the image first if you need a different shape
4Input images must have an aspect ratio between 1:2.5 and 2.5:1 with each side at least 300px
5Use the seed parameter to reproduce a result you like while tweaking the prompt

Use Cases

Animating a still image as the opening frame of a video
Character-consistent scenes built from multiple reference images
Short-form vertical (9:16) content for social media
Product showcase videos combining reference shots
Cinematic text-to-video clips up to 15 seconds