HappyHorse 1.1

About

HappyHorse 1.1 is Alibaba's premium video model on Sogni, with separate text-to-video, image-to-video, and reference-to-video model IDs.

It renders 3–15 second videos at fixed 24 fps in 720p or 1080p, across nine aspect ratios, with native synchronized audio always generated.

HappyHorse accepts image references only: no references for text-to-video, one first-frame image for image-to-video, and 1–9 image references for reference-to-video. It does not accept reference videos or reference audio.

Variants

HappyHorse 1.1 ships as 3 workflow variants. Pick the input mode that fits, or start with the default.

Prompting tips

HappyHorse performs best when the prompt is compact and explicit about motion, references, camera, and lighting.

• Text to video — Describe one complete scene, including the subject, action, environment, camera move, and lighting cue.
• Image to video — Treat the source image as the fixed first frame and describe only the movement, lighting shift, and camera change.
• Reference to video — Assign roles to references as [Image 1] through [Image 9], then describe the composition, action, and camera or lighting cue.

Pricing

HappyHorse 1.1 is a pay-as-you-go Premium Spark vendor model. Every clip uses purchased Spark, including for Sogni Unlimited members. Unlimited saves 5%; Unlimited Pro saves 10%.

API

One Sogni API key reaches every model on the Supernet — call HappyHorse 1.1 with the exact model id for the variant you want.

import { SogniClient } from '@sogni-ai/sogni-client';

const client = await SogniClient.createInstance({
  appId: crypto.randomUUID(),
  apiKey: process.env.SOGNI_API_KEY,
  network: 'fast',
});

const project = await client.projects.create({
  type: 'video',
  modelId: 'happyhorse-1.1-t2v',
  positivePrompt: 'a slothicorn surfing a wave of liquid paint, slow push-in, cinematic',
  numberOfMedia: 1,
  duration: 5,
});

const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24h

curl https://api.sogni.ai/v1/creative-agent/workflows \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SOGNI_API_KEY" \
  -d '{
    "input": {
      "title": "First render",
      "steps": [{
        "id": "step1",
        "toolName": "generate_video",
        "arguments": { "prompt": "a slothicorn surfing a wave of liquid paint, slow push-in, cinematic", "videoModel": "happyhorse-1.1-t2v", "duration": 5 }
      }]
    },
    "confirm_cost": true
  }'

Example uses happyhorse-1.1-t2v. Use any exact model id from the Variants table above. Full reference at docs.sogni.ai.