Modify Video | AI Video Enhancement API

Luma Modify Video

Luma Modify Video is an AI-powered video transformation model that restyles and modifies existing videos using text prompts. Choose from multiple transformation modes — from subtle enhancements to dramatic reimaginations — and let AI transform your footage into something new.

Why Choose This?

Flexible transformation modes 9 different modes across 3 categories (Adhere, Flex, Reimagine) to control how closely the output follows your source video.
Text-guided modifications Use natural language prompts to guide the video transformation with built-in Prompt Enhancer support.
First frame control Optionally provide a modified first frame to guide the entire video transformation style.
High-quality output Produces smooth, coherent video modifications with consistent styling throughout.
Fast processing Optimized for quick turnaround times.

Parameters

Parameter	Required	Description
video	Yes	Source video to modify (max 100MB, max 30 seconds)
prompt	No	Text instruction to guide how the video should be modified
mode	No	Transformation intensity (default: adhere_1)
first_frame	No	Modified first frame image to guide the video transformation

Mode Options

Adhere (1-3) — Very close to original, ideal for subtle enhancements and minor adjustments
Flex (1-3) — Allows stylistic changes while keeping recognizable elements from the source
Reimagine (1-3) — Loosely follows the source, best for dramatic or transformative changes

Higher numbers within each category indicate stronger effect intensity.

How to Use

Upload your video — drag and drop or paste a public URL (max 30 seconds, max 100MB).
Write your prompt — describe the desired transformation or style.
Select mode — choose from adhere, flex, or reimagine based on how much change you want.
Add first frame (optional) — upload a modified first frame to guide the overall style.
Run — submit and download the transformed video.

Pricing

Per-5-second billing with a 5-second minimum.

Video Duration	Cost
Up to 5s	$0.095
10s	$0.19
15s	$0.285
20s	$0.38
30s (max)	$0.57

Billing Rules

Minimum charge: 5 seconds ($0.095)
Rate: $0.019 per second ($0.095 per 5 seconds)
Maximum video length: 30 seconds

Best Use Cases

Style Transfer — Transform realistic footage into anime, painting, or cinematic styles.
Visual Effects — Add atmospheric effects, color grading, or artistic filters to videos.
Content Repurposing — Restyle existing content for different platforms or audiences.
Creative Exploration — Experiment with dramatic reimaginations of source material.
Brand Consistency — Apply consistent visual styles across multiple video clips.

Pro Tips

Start with adhere modes for subtle changes, move to flex or reimagine for more dramatic effects.
The first_frame parameter can significantly influence the overall style of the output.
Use clear, descriptive prompts that specify the desired transformation style.
For best results, use high-quality source videos with good lighting.

Notes

Maximum video file size is 100MB.
Maximum video duration is 30 seconds.
If using a URL, ensure it is publicly accessible.

Modify Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/luma/modify-video 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 Modify Video below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/luma/modify-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "mode": "adhere_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("luma/modify-video", {
        "video": "https://example.com/your-input.mp4",
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "mode": "adhere_1"
});

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

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "luma/modify-video",
    {
    "video": "https://example.com/your-input.mp4",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "mode": "adhere_1"
}
)

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

Modify Video API — Frequently asked questions

What is the Modify Video API?

Modify Video is a Luma model for video editing, exposed as a REST API on WaveSpeedAI. Luma Modify Video transforms and restyles existing videos with AI-powered modifications, enabling style changes, visual enhancements, and creative edits. 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 Modify Video 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/luma/luma-modify-video.

How much does Modify Video cost per run?

Modify Video starts at $0.095 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 Modify Video accept?

Key inputs: `prompt`, `video`, `first_frame`, `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/luma/luma-modify-video.

How long does Modify Video take to generate?

Average end-to-end generation time on WaveSpeedAI is around 163 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Modify Video outputs commercially?

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

PrzykładyZobacz wszystkie

Powiązane modele

README