MiniMax H3 Open Weights | Try in Video Generator →

Wan 2.7 Video Edit | AI Video Enhancement API

alibaba/

WAN 2.7 Video Edit performs prompt-driven video editing with multi-image reference support, supporting 720p/1080p output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

video-to-video
Input

Idle

$0.5per run·~20 / $10

Next:

ExamplesView all

Change the motorcycle's color to blue.

replace the main subject with a blonde woman

Related Models

README

Wan 2.7 Video Edit

Wan 2.7 Video Edit performs prompt-driven editing on existing videos with optional multi-image reference support. Upload a source video, describe the desired edits in natural language, and optionally provide reference images to guide the target style or element appearance — the model applies precise, context-aware edits while preserving motion and temporal consistency throughout the clip.

Why Choose This?

  • Natural-language video editing Describe your edit in plain text — swap colors, change objects, alter styles — without manual masking or keyframing.

  • Multi-image reference support Upload 1 to 9 reference images to guide the target element, style, or appearance in the edited output.

  • Audio control Choose between auto mode (model decides) or origin to preserve the original audio track.

  • Negative prompt support Specify what to avoid in the edit for more precise control over the output.

  • Prompt expansion Enable enable_prompt_expansion to let the model automatically enrich and optimize your prompt before generation.

  • Resolution options Generate at 720p or 1080p to match your delivery requirements.

Parameters

ParameterRequiredDescription
videoYesSource video to edit (URL or file upload).
promptYesText description of the desired edits.
imagesNoReference images to guide editing (1–9 images). Click Add Item for more.
negative_promptNoElements to exclude from the edited video.
resolutionNoOutput resolution: 720p (default) or 1080p.
durationNoOutput duration in seconds. Default 0 = same as input video. Set 2–10 to trim from the start to the specified length.
audio_settingNoAudio mode: auto (default, model decides) or origin (keep original audio).
enable_prompt_expansionNoEnable automatic prompt optimization before generation. Default: off.
seedNoRandom seed for reproducible results. Use -1 for a random seed.

How to Use

  1. Upload your video — provide the source clip to edit via URL or drag-and-drop.
  2. Write your prompt — describe exactly what should change (e.g., "Change the motorcycle's color to blue.").
  3. Add reference images (optional) — upload images to guide the look of elements or styles in the edit.
  4. Add negative prompt (optional) — specify elements you want to exclude from the output.
  5. Select resolution — 720p for standard output, 1080p for higher-quality results.
  6. Set duration (optional) — leave at 0 to match the input video length, or set 2–10 to trim.
  7. Set audio_setting (optional) — choose auto or origin to preserve original audio.
  8. Enable prompt expansion (optional) — let the model automatically enrich your prompt.
  9. Set seed (optional) — fix the seed to reproduce a specific result in future runs.
  10. Submit — generate, preview, and download your edited video.

Pricing

Duration720p1080p
5s$0.50$0.75
10s$1.00$1.50

Billing Rules

  • 720p: $0.10 per second
  • 1080p: $0.15 per second (1.5× base rate)
  • Minimum billed duration: 2 seconds
  • Maximum billed duration: 10 seconds

Best Use Cases

  • Color & Style Changes — Swap object colors, materials, or visual styles across the entire clip.
  • Object Replacement — Replace specific elements in the video with different objects or variants.
  • Scene Adjustments — Change background mood, lighting, or environment without reshooting.
  • E-commerce — Edit product videos to showcase different variants or settings from a single source clip.
  • Content Iteration — Rapidly test multiple edit directions on the same source footage.

Pro Tips

  • Be specific and descriptive in your prompt — the more detail you provide, the more accurate the edit.
  • Upload reference images when you want the model to match a specific target appearance or style.
  • Use negative_prompt to prevent edits from bleeding into areas you want to preserve.
  • Enable prompt expansion for shorter or less detailed prompts to get richer output automatically.
  • Use 720p to test your edit direction before committing to a 1080p final render.

Notes

  • Both video and prompt are required fields; all other parameters are optional.
  • Billed duration is clamped between 2 and 10 seconds regardless of actual video length.
  • Ensure video and image URLs are publicly accessible if using links rather than direct uploads.
  • Please ensure your content complies with usage policies.

Related Models

Note:This website uses AI models provided by third parties.

Wan 2.7 Video Edit API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.7/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 Wan 2.7 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",
    "duration": 0,
    "audio_setting": "auto",
    "enable_prompt_expansion": false,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.7/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=$(printf '%s' "$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/wan-2.7/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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "resolution": "720p",
        "duration": 0,
        "audio_setting": "auto",
        "enable_prompt_expansion": false,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "resolution": "720p",
    "duration": 0,
    "audio_setting": "auto",
    "enable_prompt_expansion": False,
    "seed": -1
}

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/wan-2.7/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 = 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)

Wan 2.7 Video Edit API — Frequently asked questions

What is the Wan 2.7 Video Edit API?

Wan 2.7 Video Edit is a Alibaba model for video editing, exposed as a REST API on WaveSpeedAI. WAN 2.7 Video Edit performs prompt-driven video editing with multi-image reference support, supporting 720p/1080p output. 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 Wan 2.7 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 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-wan-2.7-video-edit.

How much does Wan 2.7 Video Edit cost per run?

Wan 2.7 Video Edit starts at $0.50 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 Wan 2.7 Video Edit accept?

Key inputs: `prompt`, `images`, `video`, `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-wan-2.7-video-edit.

How do I get started with the Wan 2.7 Video Edit API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Wan 2.7 Video Edit 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.