Pruna AI P-Video Animate API

Pruna AI P-Video Animate

Pruna AI P-Video Animate transfers motion from a source video onto a reference image to generate an animated video clip. It is designed for motion-driven character animation, stylized performance clips, social media content, and other workflows where you want a static image to follow the movement of an existing video.

Why Choose This?

Motion transfer workflow Use a source video to drive motion while preserving the subject or scene from a reference image.
Image-guided animation Start from a single image and generate a video with matched movement.
Flexible frame rate options Keep the original frame rate or choose 24 or 48 FPS for output delivery needs.
Resolution control Choose 720p or 1080p depending on quality and budget.
Optional audio preservation Enable save_audio when you want the exported video to include audio.
Seed support Use seed for more reproducible animation results.

Parameters

Parameter	Required	Description
video	Yes	Source motion video URL.
image	Yes	Reference image URL for the subject or scene to animate.
prompt	No	Optional instruction describing how the image should follow the source video motion. Default: `Animate the reference subject using the motion from the source video.`
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`.
seed	No	Random seed for reproducible generations. Default: `-1`.

How to Use

Upload your source motion video — provide the clip whose movement should be transferred.
Upload your reference image — provide the character, subject, or scene you want to animate.
Add a prompt (optional) — describe the desired motion behavior or stylistic handling.
Choose resolution — use 720p for lower cost or 1080p for higher quality.
Choose frame rate (optional) — keep original or select 24 or 48 FPS.
Set audio and seed (optional) — keep audio if needed and use a fixed seed for reproducibility.
Submit — run the model and download the animated video.

Example Prompt

Animate the portrait subject using the motion from the source video, keeping facial identity stable and body movement natural.

Pricing

Pricing depends on source video duration and resolution.

Billing Rules

Billing is based on the uploaded source video duration
Billed duration is rounded up to the next whole second
Maximum billed duration is 20 seconds
Minimum billed duration is 1 second
720p costs $0.03 per billed second
1080p costs $0.06 per billed second
fps, save_audio, prompt, and seed 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 animation — Transfer live-action motion onto an illustrated or stylized character.
Avatar content — Animate a still portrait using source video performance.
Creative prototyping — Test how a static design behaves under real movement.
Social media clips — Turn still art or portraits into short motion-driven videos.
Performance transfer — Apply gestures, posture, and body motion from one clip to another subject.

Pro Tips

Use a clear reference image with a well-defined subject.
Choose a source motion video with readable, stable movement for cleaner transfer.
Keep the prompt simple and focused on motion behavior when possible.
Use 720p for fast iteration and 1080p for higher-quality final output.
Shorter source clips are good for testing before processing longer motion references.
Reuse the same seed when comparing prompt changes on the same inputs.

Notes

video and image are required.
Pricing is based on the source video duration, capped at 20 seconds.
save_audio controls whether the exported video includes audio, but does not affect pricing.
seed = -1 means random generation.
The generated output follows the motion source rather than a freeform prompt-only animation path.

Related Models

Pruna AI P-Video Image-to-Video — Generate motion from a reference image and prompt without a source motion video.
Pruna AI P-Video Text-to-Video — Generate videos directly from text prompts.
Pruna AI P-Image Text-to-Image — Generate still images for image-first creative workflows.

P Video Animate API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pruna-ai/p-video/animate 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 Animate below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-video/animate" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4",
    "image": "https://example.com/your-input.jpg",
    "prompt": "Animate the reference subject using the motion from the source video.",
    "resolution": "720p",
    "fps": "original",
    "save_audio": true,
    "seed": -1
}'

# 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/animate", {
        "video": "https://example.com/your-input.mp4",
        "image": "https://example.com/your-input.jpg",
        "prompt": "Animate the reference subject using the motion from the source video.",
        "resolution": "720p",
        "fps": "original",
        "save_audio": true,
        "seed": -1
});

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

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "pruna-ai/p-video/animate",
    {
    "video": "https://example.com/your-input.mp4",
    "image": "https://example.com/your-input.jpg",
    "prompt": "Animate the reference subject using the motion from the source video.",
    "resolution": "720p",
    "fps": "original",
    "save_audio": true,
    "seed": -1
}
)

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

P Video Animate API — Frequently asked questions

What is the P Video Animate API?

P Video Animate is a Pruna Ai model for pose / motion driven video, exposed as a REST API on WaveSpeedAI. Pruna AI P-Video Animate is a fast AI video animation model that animates images and visual assets using the Pruna p-video-animate workflow running on RunPod. Ready-to-use REST inference API for image animation, character motion, product visuals, social media clips, marketing creatives, and professional AI video generation 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 Animate 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-animate.

How much does P Video Animate cost per run?

P Video Animate 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 Animate accept?

Key inputs: `prompt`, `image`, `video`, `resolution`, `fps`, `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/pruna-ai/pruna-ai-p-video-animate.

How do I get started with the P Video Animate 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 Animate 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