Seedream 5.0 Pro sudah LIVE | Coba di Generator Gambar →

HappyHorse 1.1 Text to Video API

alibaba /

Alibaba HappyHorse 1.1 Text-to-Video generates cinematic 720P or 1080P videos from text prompts, with smooth camera movement, expressive motion, and strong prompt fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-video
Input

Siap

$0.7per run·~14 / $10

Selanjutnya:

ContohLihat semua

A luxury perfume bottle standing on black marble, surrounded by white roses, soft mist, silver reflections, elegant high-end commercial photography, dramatic spotlight. Mist rolls across the marble surface as rose petals fall around the perfume bottle. A beam of light sweeps over the glass, revealing reflections and liquid movement inside the bottle. Smooth luxury product commercial motion.

Model Terkait

README

Alibaba Happy Horse 1.1 Text-to-Video

Alibaba Happy Horse 1.1 Text-to-Video turns natural-language prompts into cinematic videos with smooth motion, strong prompt alignment, and stable subject rendering. It supports both 720p and 1080p output, along with multiple aspect ratios for ad creatives, social content, storytelling, and concept work.

Why Choose This?

  • Strong prompt fidelity
    Follows detailed instructions for scene composition, action, lighting, mood, and camera movement.

  • Cinematic motion
    Generates smooth, expressive motion with stable subjects and polished visual dynamics.

  • Flexible aspect ratios
    Supports 16:9, 9:16, 1:1, 4:3, and 3:4 for landscape, portrait, and square video formats.

  • Resolution options for different needs
    Choose 720p for lower-cost iteration or 1080p for higher-resolution outputs.

  • Production-ready API
    Access the model through a REST inference API for easy integration into creative workflows.

Parameters

ParameterRequiredDescription
promptYesText prompt describing the desired video. Maximum 2500 characters.
aspect_ratioNoOutput aspect ratio: 16:9 default, 9:16, 1:1, 4:3, or 3:4.
resolutionNoOutput resolution: 720p default or 1080p.
durationNoVideo length in seconds. Range: 3–15, default 5.
seedNoRandom seed for reproducibility. Range: 0–2147483647.

How to Use

  1. Write your prompt — Describe the scene, subject, action, camera movement, lighting, and mood.
  2. Choose aspect ratio — Select the format that best matches your target platform or creative layout.
  3. Choose resolution — Use 720p for lower-cost iteration or 1080p for higher-resolution output.
  4. Set duration — Choose a clip length between 3 and 15 seconds.
  5. Set a seed optional — Use a fixed seed if you want more reproducible results.
  6. Submit — Generate and download your video.

Example Prompt

A cinematic street scene at night, light rain falling, soft reflections on wet pavement, a stylish woman walking slowly toward the camera, gentle dolly-in movement, neon glow, shallow depth of field, elegant and atmospheric mood.

Pricing

Per 5 Seconds

ResolutionCost
720p$0.70
1080p$0.945

Per Second

ResolutionCost
720p$0.14
1080p$0.189

Example Costs

Resolution3s5s10s15s
720p$0.42$0.70$1.40$2.10
1080p$0.567$0.945$1.89$2.835

Best Use Cases

  • Ad creatives — Generate short cinematic promo videos from detailed campaign concepts.
  • Social media content — Create vertical, square, or landscape videos for different platforms.
  • Concept visualization — Turn written ideas into motion previews for pitching, ideation, or storyboarding.
  • Brand storytelling — Build polished mood-driven clips with specific lighting, movement, and atmosphere.
  • Creative prototyping — Explore different visual directions before committing to full production.
  • Short-form cinematic scenes — Generate expressive clips for teasers, motion concepts, and narrative experiments.

Pro Tips

  • Be specific in your prompt about subject, action, camera movement, lighting, and mood.
  • Mention visual style clearly, such as cinematic, commercial, dreamy, realistic, or editorial.
  • Use 720p for rapid testing, then switch to 1080p for higher-resolution outputs.
  • Pick the aspect ratio based on the final destination: 9:16 for short-form mobile, 16:9 for widescreen, and 1:1 for square layouts.
  • Reuse the same seed when you want more reproducible outputs.
  • Start with shorter durations to validate motion and composition before generating longer clips.

Related Models

Catatan:Situs web ini menggunakan model AI yang disediakan oleh pihak ketiga.

Happyhorse 1.1 Text To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/happyhorse-1.1/text-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Happyhorse 1.1 Text To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/happyhorse-1.1/text-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/alibaba/happyhorse-1.1/text-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "aspect_ratio": "16:9",
        "resolution": "720p",
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/alibaba/happyhorse-1.1/text-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Happyhorse 1.1 Text To Video API — Frequently asked questions

What is the Happyhorse 1.1 Text To Video API?

Happyhorse 1.1 Text To Video is a Alibaba model for video generation, exposed as a REST API on WaveSpeedAI. Alibaba HappyHorse 1.1 Text-to-Video generates cinematic 720P or 1080P videos from text prompts, with smooth camera movement, expressive motion, and strong prompt fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Happyhorse 1.1 Text To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-happyhorse-1.1-text-to-video.

How much does Happyhorse 1.1 Text To Video cost per run?

Happyhorse 1.1 Text To Video starts at $0.70 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Happyhorse 1.1 Text To Video accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `seed`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-happyhorse-1.1-text-to-video.

How long does Happyhorse 1.1 Text To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 162 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Happyhorse 1.1 Text To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.