MiniMax H3 Open Weights | Try in Video Generator →

Swap | AI Portrait Transfer API

pixverse/

PixVerse Swap replaces backgrounds, people, and objects directly inside existing videos for quick scene changes and creative edits with natural-looking results. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

portrait-transfer
Input

Idle

$0.09per run·~11 / $1

ExamplesView all

Related Models

README

PixVerse Swap — Video Swap Model

PixVerse Swap generates high-quality video clips by swapping the person, objects, or background of a source video using a reference image. It preserves the original motion, timing, and camera work while replacing the visual target with the new look from the image.

What it does

  • Takes a source video (performance, camera motion, timing).
  • Takes a reference image (new person, object, or background).
  • Replaces the selected target in the video with the content from the image.
  • Keeps motion, expressions, and framing consistent so the edit feels natural.

Ideal for:

  • Turning talking-head videos into stylized or character performances
  • Swapping outfits, props, or featured products
  • Dropping your subject into new scenes without reshooting

Inputs and Controls

  • video (required) Source clip whose motion, expressions, and timing you want to keep.

  • image (required) Reference image that defines the new person, object, or background.

  • resolution

  • 360p

  • 540p

  • 720p

  • mode

  • person – Replace the main person in the video with the person or character from the image.

  • object – Replace a key object (for example, smartphone, product, prop) with the object in the image.

  • background – Keep the subject but replace the scene behind them using the reference image.

Pricing

ResolutionSwap price per second
360p$0.090
540p$0.090
720p$0.120
  • P.S: $0.020 per request for mask selection (charged once per job).

How to Use

  1. Upload or paste the URL of your source video.
  2. Upload or paste the URL of the reference image that contains the new person, object, or background.
  3. Choose the resolution (360p, 540p, or 720p) according to your quality and cost needs.
  4. Select the mode:
  • person for full character swap,
  • object for prop/product replacement,
  • background to move your subject into a different environment.
  1. Click Run and wait for the processed video to appear in the preview panel.
  2. Review the result and download if you are satisfied.

Notes

  • An uploaded video in supported formats (mp4, mov)
  • Max resolution: 1920
  • Max file size: 50MB
  • Max duration: 30 seconds
Note:This website uses AI models provided by third parties.

Swap API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pixverse/swap 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 Swap below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "resolution": "720p",
    "mode": "person"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/pixverse/swap" \
  -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/pixverse/swap";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "resolution": "720p",
        "mode": "person"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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 = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "resolution": "720p",
    "mode": "person"
}

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/pixverse/swap", 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)

Swap API — Frequently asked questions

What is the Swap API?

Swap is a Pixverse model for AI inference, exposed as a REST API on WaveSpeedAI. PixVerse Swap replaces backgrounds, people, and objects directly inside existing videos for quick scene changes and creative edits with natural-looking results. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Swap 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/pixverse/pixverse-swap.

How much does Swap cost per run?

Swap starts at $0.090 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 Swap accept?

Key inputs: `image`, `video`, `resolution`, `mode`. 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/pixverse/pixverse-swap.

How do I get started with the Swap 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 Swap outputs commercially?

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