HappyHorse 1.0 Video Edit | AI Video Editing API

alibaba/happyhorse-1.0/video-edit

Alibaba Happy Horse 1.0 (Video Edit) performs prompt-driven video editing with multi-image reference support, supporting 720p/1080p output. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Video Editing
Input

Drag & drop or click to upload

Idle

$0.28per run·~35 / $10

Next:

ExamplesView all

Change the setting in the video to a fashion runway.

Related Models

README

Alibaba Happy Horse 1.0 Video Edit

Alibaba Happy Horse 1.0 Video Edit performs prompt-driven editing on existing videos, with optional multi-image reference support for stronger visual guidance and identity consistency. Upload a source video, describe the desired edits, and the model generates a transformed video clip in 720p or 1080p.

Why Choose This?

  • Prompt-driven video editing Edit existing videos using natural-language instructions for style, mood, action, and visual transformation.

  • Optional reference-image support Add up to multiple reference images to better guide character appearance, style consistency, and visual identity.

  • Consistent output workflow Keep the structure of the original video while transforming its look, atmosphere, or subject details.

  • Flexible resolution options Choose 720p for lower-cost iteration or 1080p for higher-quality final outputs.

  • Production-ready API Access the model through a REST inference API with no cold starts for scalable creative workflows.

Parameters

ParameterRequiredDescription
videoYesSource video to edit.
promptYesText description of the desired edits.
imagesNoOptional reference images. Supports 0–9 images.
resolutionNoOutput resolution: 720p (default) or 1080p.
seedNoRandom seed for reproducibility. Range: 0–2147483647.

How to Use

  1. Upload your source video — provide the video you want to edit.
  2. Write your prompt — describe the desired transformation, including style, scene changes, atmosphere, or subject adjustments.
  3. Add reference images (optional) — upload 0–9 images if you want stronger control over identity, styling, or visual direction.
  4. Choose resolution — use 720p for lower-cost iteration or 1080p for higher-quality output.
  5. Set a seed (optional) — use a fixed seed for more reproducible edits.
  6. Submit — generate and download the edited video.

Example Prompt

Transform this street video into a cinematic neo-noir scene with rainy atmosphere, stronger reflections on the ground, richer contrast, subtle slow-motion feeling, dramatic lighting, and a premium commercial look

Pricing

ResolutionPer second3s5s10s30s60s
720p$0.28$0.84$1.40$2.80$8.40$16.80
1080p$0.48$1.44$2.40$4.80$14.40$28.80

Billing Rules

  • Billed duration: the source video duration, clamped to 3–60 seconds (the output matches the source length)
  • When the source video is > 60s: the system automatically trims it to the first 60s
  • Total price: per-second rate × billed duration

Best Use Cases

  • Style transformation — Rework existing footage into new visual styles, moods, or cinematic looks.
  • Ad creative adaptation — Turn one source video into multiple campaign variations with different art directions.
  • Character and identity guidance — Use reference images to better preserve appearance and branding cues.
  • Content repurposing — Refresh older video assets for new promotions, launches, or platform formats.
  • Social media optimization — Quickly generate visually distinct edits from the same original clip.
  • Creative prototyping — Explore multiple editing directions before committing to a full post-production workflow.

Pro Tips

  • Use a clear source video with stable framing for more predictable edits.
  • Be specific in your prompt about what should change and what should remain consistent.
  • Add reference images when character appearance, outfit details, or brand styling need tighter control.
  • Use 720p for fast testing, then switch to 1080p for final-quality outputs.
  • Reuse the same seed when you want more reproducible edits.
  • Keep important edit instructions concrete, such as lighting changes, style shifts, color mood, or scene atmosphere.

Notes

  • Both video and prompt are required.
  • images is optional and supports 0–9 reference images.
  • Ensure all video and image URLs are publicly accessible.
  • Output video duration is limited to 3–60 seconds.
  • When the input video exceeds 60 seconds, the system automatically trims it to the first 60 seconds.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Happyhorse 1.0 Video Edit API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/happyhorse-1.0/video-edit 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 1.0 Video Edit 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",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "resolution": "720p"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/happyhorse-1.0/video-edit" \
  -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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 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' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/alibaba/happyhorse-1.0/video-edit";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "resolution": "720p"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  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",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "resolution": "720p"
}

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-1.0/video-edit", 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 = 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", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Happyhorse 1.0 Video Edit API — Frequently asked questions

What is the Happyhorse 1.0 Video Edit API?

Happyhorse 1.0 Video Edit is a Alibaba model for video editing, exposed as a REST API on WaveSpeedAI. Alibaba Happy Horse 1.0 (Video Edit) performs prompt-driven video editing with multi-image reference support, supporting 720p/1080p output. Ready-to-use REST 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 1.0 Video Edit 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-happyhorse-1.0-video-edit.

How much does Happyhorse 1.0 Video Edit cost per run or per second?

Happyhorse 1.0 Video Edit starts at $0.28 per run or per second. 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 1.0 Video Edit accept?

Key inputs: `prompt`, `images`, `video`, `resolution`, `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-1.0-video-edit.

How long does Happyhorse 1.0 Video Edit take to generate?

Reported generation time on WaveSpeedAI is around 144 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.

Can I use Happyhorse 1.0 Video Edit outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Alibaba). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — alibaba/happyhorse-1.0/video-edit for AI agents and LLMs