Live Memory | Trending Video Effects API

Live Memory Effect

Requirements

Number of Images

Mandatory
Only one image upload supported

Number of People

Supports single or multiple product images

Image Requirements

Best for front-facing human figures with simple poses and clear photos

Prompt

Mandatory
Format should remain unchanged as much as possible
If custom requirements exist, modify the prompt without altering the structure and majority of the content

Effect Boundaries

Possible minor movements like blinking/smiling without significant motion
Props carried by subjects might deform

Best Practices

Use clear, front-facing photos
Ensure all subjects are clearly visible
Use simple poses for optimal results
Keep the default prompt structure
Avoid complex backgrounds

Live Memory API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/video-effects/live-memory 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 Live Memory below.

HTTP example

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

# 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("video-effects/live-memory", {
        "image": "https://example.com/your-input.jpg"
});

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

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "video-effects/live-memory",
    {
    "image": "https://example.com/your-input.jpg"
}
)

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

Live Memory API — Frequently asked questions

What is the Live Memory API?

Live Memory is a Video Effects model for AI inference, exposed as a REST API on WaveSpeedAI. Image-to-Video: Create dynamic living memory videos from photos with natural motion and emotional animation, turning still images into immersive short clips. 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 Live Memory 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/video-effects/video-effects-live-memory.

How much does Live Memory cost per run?

Live Memory 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 Live Memory accept?

Key inputs: `image`. 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/video-effects/video-effects-live-memory.

How long does Live Memory take to generate?

Average end-to-end generation time on WaveSpeedAI is around 1800 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Live Memory outputs commercially?

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

ExamplesView all

Related Models

README