HappyHorse 1.1

HappyHorse 1.1 text-to-video — 3–15s at 720p/1080p, 9 aspect ratios incl. 21:9/9:21, per-second pricing.

Credits

Use HappyHorse 1.1 in Nodaro

Add one of these nodes to your canvas, open its settings, and choose HappyHorse 1.1 as the model:

• Generate Video

Run HappyHorse 1.1 from code

Each call starts a job and returns its jobId. Poll GET /v1/jobs/:id/status, or let the SDK wait for the result. A run costs the credits on this page. API reference

With Nodaro connected to Claude, ChatGPT or Cursor, ask in plain words, or have the assistant call the tool: “Use HappyHorse 1.1 to make: A paper boat drifts down a rain-soaked street at dusk, slow dolly in”

curl -s -X POST https://app.nodaro.ai/v1/text-to-video \  -H "Authorization: Bearer $NODARO_API_KEY" \  -H "Content-Type: application/json" \  -d '{        "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",        "provider": "happyhorse",        "duration": 3      }'

import { createClient, StaticTokenAuth } from "@nodaro/sdk"const client = createClient({  baseUrl: "https://app.nodaro.ai",  auth: new StaticTokenAuth(process.env.NODARO_API_KEY!),})const output = await client.nodes.runAndWait("text-to-video", {  prompt: "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",  provider: "happyhorse",  duration: 3,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "happyhorse",    "duration": 3  }}

Prompt tips

• Any-language prompts up to 5000 chars (2500 Chinese) — excess is silently truncated, so front-load subject → action → scene → camera → style.
• 3-15 seconds per second of billing; 720p or 1080p; ratios 16:9 / 9:16 / 1:1 / 4:3 / 3:4. Pick the shortest duration that serves the shot.
• ref2v is one of the few true REFERENCE modes on the roster: wired refs keep identity across the clip — bind each reference explicitly in the prompt.
• No published vendor style guide — the platform's standard structure applies; keep one camera move per shot and quantify motion physically.

Similar models