Pruna AI P-Video Replace API

Pruna AI P-Video Replace

Pruna AI P-Video Replace replaces or inserts a reference subject into a source video while preserving the original motion. Upload one source video, add one to three reference images, and use a prompt to describe how the subject should appear in the final result. It is suitable for character replacement, identity transfer, stylized casting swaps, and other motion-preserving video editing workflows.

Why Choose This?

Reference-guided subject replacement
Use one to three reference images to replace or insert a person or subject into an existing video.
Motion-preserving editing
Keep the motion from the source video while changing who appears in the scene.
Simple replacement workflow
Upload a video, add reference images, describe the replacement, and generate the edited result.
Flexible output settings
Choose 720p or 1080p, select frame rate behavior, and optionally keep the output audio.
Production-ready API
Useful for creator workflows, identity transfer, stylized edits, promo content, and fast concept testing.

Parameters

Parameter	Required	Description
video	Yes	Source video URL.
images	Yes	Reference image URLs for replacement. Supports `1` to `3` images.
prompt	No	Instruction describing how the reference image should be placed into the video. Default: `Place the reference person into the video while preserving the original motion.`
resolution	No	Output video resolution. Supported values: `720p`, `1080p`. Default: `720p`.
fps	No	Target output frame rate. Supported values: `original`, `24`, `48`. Default: `original`.
save_audio	No	Save the output video with audio. Default: `true`.

How to Use

Upload the source video — provide the clip whose motion you want to preserve.
Upload reference images — add 1 to 3 images of the person or subject you want to insert or replace.
Write the prompt (optional) — describe how the replacement should appear in the scene.
Choose resolution — use 720p for lower cost or 1080p for higher quality.
Choose frame rate (optional) — keep the original FPS or switch to 24 or 48.
Choose audio behavior (optional) — keep save_audio=true if you want the output video to include audio.
Submit — run the model and download the generated video.

Example Prompt

Place the reference person into the video while preserving the original motion, body rhythm, and scene timing. Keep the result natural and consistent with the original lighting.

Pricing

Pricing depends on source video duration and resolution.

Billing Rules

Billing is based on the uploaded source video duration
Minimum billed duration is 1 second
720p costs $0.03 per billed second
1080p costs $0.06 per billed second
images, prompt, fps, and save_audio do not affect pricing

Example Costs

Resolution	1s	5s	10s	20s
720p	$0.03	$0.15	$0.30	$0.60
1080p	$0.06	$0.30	$0.60	$1.20

Best Use Cases

Character replacement — Replace a subject in a video while preserving the original motion.
Identity transfer — Apply the appearance of a reference person to an existing performance clip.
Stylized casting swaps — Test alternate talent or character looks without reshooting.
Creator and promo edits — Produce fast replacement-based edits for campaigns, shorts, or social content.
Concept prototyping — Quickly validate motion-preserving replacement ideas from simple inputs.

Pro Tips

Use clear reference images with a consistent face angle and lighting when identity matters.
Choose a source video with readable body motion for better replacement stability.
Start with one strong reference image before adding multiple references.
Keep the prompt focused on identity placement and realism instead of over-describing the scene.
Use 720p for quick testing and 1080p for higher-quality final outputs.

Notes

video and images are required.
images supports 1 to 3 reference images.
save_audio controls whether the output video includes audio, but does not affect pricing.
Billing uses the source video duration with a minimum of 1 second.
Pricing depends only on source video duration and selected resolution.

Related Models

Pruna AI P-Video Animate — Animate a reference image using motion from a source video.
Pruna AI P-Video Image-to-Video — Generate a video from a reference image and prompt.
Pruna AI P-Video Text-to-Video — Generate videos directly from natural-language prompts.
Pruna AI P-Image Edit — Edit still images with natural-language instructions.

P Video Replace API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pruna-ai/p-video/replace 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 P Video Replace below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-video/replace" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4",
    "prompt": "Place the reference person into the video while preserving the original motion.",
    "resolution": "720p",
    "fps": "original",
    "save_audio": true
}'

# 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("pruna-ai/p-video/replace", {
        "video": "https://example.com/your-input.mp4",
        "prompt": "Place the reference person into the video while preserving the original motion.",
        "resolution": "720p",
        "fps": "original",
        "save_audio": true
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "pruna-ai/p-video/replace",
    {
    "video": "https://example.com/your-input.mp4",
    "prompt": "Place the reference person into the video while preserving the original motion.",
    "resolution": "720p",
    "fps": "original",
    "save_audio": true
}
)

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

P Video Replace API — Frequently asked questions

What is the P Video Replace API?

P Video Replace is a Pruna Ai model for AI inference, exposed as a REST API on WaveSpeedAI. Pruna AI P-Video Replace is a fast AI video subject replacement model that replaces or inserts reference subjects into a source video while preserving the original motion, timing, and optional audio. Ready-to-use REST inference API for video subject replacement, character insertion, product placement, creative video editing, advertising creatives, social media content, and professional video editing workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the P Video Replace 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/pruna-ai/pruna-ai-p-video-replace.

How much does P Video Replace cost per run?

P Video Replace starts at $0.030 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 P Video Replace accept?

Key inputs: `prompt`, `images`, `video`, `resolution`, `fps`, `save_audio`. 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/pruna-ai/pruna-ai-p-video-replace.

How do I get started with the P Video Replace 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 P Video Replace outputs commercially?

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

BeispieleAlle anzeigen

Ähnliche Modelle

README