How to Use the HappyHorse 1.1 API

HappyHorse 1.1 is a video generation model from Alibaba, now live on EmpirioLabs. It is one model with three modes, picked automatically from what you send:

• Text to video: send a prompt only.
• Image to video: attach one image to animate it.
• Reference to video: attach up to 9 reference images and refer to them in the prompt as character1, character2, and so on.

Every mode renders at 720p or 1080p for 3 to 15 seconds, with synchronized native audio. HappyHorse 1.1 improves visual quality, motion smoothness, character consistency across clips, and text rendering over the previous version.

Pricing

HappyHorse 1.1 is pay-as-you-go, billed per second of generated video, with a lower rate at 720p and a higher rate at 1080p. There is no subscription. See the live per-second rates on the HappyHorse 1.1 model page and the pricing page.

Quickstart

Video generation is asynchronous. Submit a request to get a job id, then poll until the video is ready.

curl -X POST https://api.empiriolabs.ai/v1/videos/generations \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1-1",
    "prompt": "A red fox trotting across a snowy field at sunrise, cinematic",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

The response includes a job id and a poll url. Poll it until the status is completed and a video url is returned:

curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY"

For image to video, add an image. For reference to video, pass several images and name them in the prompt:

{
  "model": "happyhorse-1-1",
  "prompt": "character1 walks through character2 at golden hour, cinematic",
  "image": ["https://example.com/portrait.jpg", "https://example.com/scene.jpg"],
  "resolution": "1080p",
  "duration": 5
}

Good to know

• One model, modes auto-detected. Send text for text to video, one image for image to video, or several images for reference to video. You can also set the mode parameter explicitly.
• Reference to video supports up to 9 images. Name them in the prompt as character1, character2, and so on for the strongest consistency.
• Image to video follows the source image for aspect ratio. Text and reference modes accept 16:9, 9:16, 1:1, 4:3, and 3:4.
• Native audio is always generated. No separate audio step is needed.
• Image input only. HappyHorse 1.1 does not take video input.

Try it now in the playground or read the full API reference.