Giảm 50% mô hình Vidu Q3 & Q3 Pro · Chỉ trên WaveSpeedAI | 20/5 – 2/6

Video Body Swap

wavespeed-ai /

Video Body Swap replaces the body in a target video with your face. Upload a face image and a body video to get a seamless swap. Ready-to-use REST inference API, no coldstarts, affordable pricing.

portrait-transfer
Input

Kéo & thả hoặc nhấp để tải lên

preview

Kéo & thả hoặc nhấp để tải lên

Idle

$0.2per run·~50 / $10

ExamplesView all

Related Models

README

Video Body Swap

Video Body Swap replaces the body in a target video with your face. Upload a face image and a body video — AI seamlessly composites your likeness onto the moving subject, frame by frame, with natural blending and consistent identity throughout the clip.

Why Choose This?

  • Seamless face-to-body compositing Advanced AI tracks the subject across every frame and blends your face naturally onto the body in motion, maintaining consistent identity and lighting.

  • Simple two-input workflow Just a face image and a body video — no masking, no manual keyframing, no technical setup required.

  • Wide range of use cases Works across talking head videos, dancing clips, fitness content, and more.

  • Production-ready API No cold starts, predictable per-second pricing, and a ready-to-use REST endpoint for seamless integration.

Parameters

ParameterRequiredDescription
imageYesFace image to composite onto the body video.
videoYesTarget body video. Billing is based on this video's duration.

How to Use

  1. Upload your face image — a clear, front-facing portrait with good lighting works best.
  2. Upload your body video — the video whose body you want to swap the face onto.
  3. Submit — AI processes the swap frame by frame and returns the finished video.

Pricing

$0.08 per second of input video, with a minimum charge of 5 seconds and a maximum billable duration of 120 seconds.

Video DurationCost
5s (minimum)$0.40
10s$0.80
30s$2.40
60s$4.80
120s (maximum)$9.60

Billing Rules

  • Minimum charge: 5 seconds
  • Maximum billable duration: 120 seconds
  • Videos longer than 120 seconds are capped at 120 seconds for billing purposes

Best Use Cases

  • Creative content — Place yourself into dance, performance, or action videos.
  • Marketing & advertising — Swap faces for personalized promotional video content.
  • Entertainment & social media — Generate fun, shareable body-swap clips for Reels and TikTok.
  • Developer integrations — Embed body swap functionality into apps and pipelines via the REST API.

Pro Tips

  • Use a high-quality, well-lit face photo with a clear, unobstructed view for the most natural compositing result.
  • Videos with a single clearly visible subject and stable lighting produce the cleanest swaps.
  • Avoid heavily cropped or low-resolution face images — the more facial detail the AI has, the better the blend.
  • For best results, the face in the image should be roughly front-facing and similar in angle to the subject in the video.

Notes

  • Both image and video are required fields.
  • Ensure URLs are publicly accessible if using links rather than direct uploads.
  • Videos longer than 120 seconds are accepted but billing is capped at 120 seconds.
  • Please ensure your content complies with WaveSpeed AI's usage policies.
Accessibility:This website uses AI models provided by third parties.

Video Body Swap API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/video-body-swap with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Video Body Swap below.

HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/video-body-swap" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "image": "https://example.com/your-input.jpg",
    "video": "https://example.com/your-input.mp4"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].
Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("wavespeed-ai/video-body-swap", {
        "image": "https://example.com/your-input.jpg",
        "video": "https://example.com/your-input.mp4"
});

console.log(result.outputs[0]); // → URL of the generated output
Python example
# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/video-body-swap",
    {
    "image": "https://example.com/your-input.jpg",
    "video": "https://example.com/your-input.mp4"
}
)

print(output["outputs"][0])  # → URL of the generated output

Video Body Swap API — Frequently asked questions

What is the Video Body Swap API?

Video Body Swap is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. Video Body Swap replaces the body in a target video with your face. Upload a face image and a body video to get a seamless swap. Ready-to-use REST inference API, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Video Body 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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/video-body-swap.

How much does Video Body Swap cost per run?

Video Body Swap starts at $0.20 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 Video Body Swap accept?

Key inputs: `image`, `video`. 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/wavespeed-ai/video-body-swap.

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

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