All models / Video / Lucy VTON 3.6 (real-time try-on)

Lucy VTON 3.6 (real-time try-on)

Name: Lucy VTON 3.6 (real-time try-on)
Brand: Decart
Price: 0.0205 USD
Availability: InStock

model id: decart/lucy-vton-3.6

Real-time · Video in → Video out realtime-video-edit

Hosts

Host	Standard	Fast	Max session
Decart	$0.0205 / s	$0.0410 / s	600 s

0% additional markup beyond our 2.5% platform fee.

Input

Garment prompt Garment image (optional)

A clean garment photo on a plain background works best. Prompt, image, or both.

Fast mode (2× rate, $0.0410/s)

Billed to your account at $0.0205/s while it runs (the session stops by itself after 120 s here). Needs a camera and a signed-in account with credits.

Output

About

Decart Lucy VTON 3.6: real-time virtual try-on on live or recorded video from a text or garment image.

Price

$0.0205 / second

per second the session is live — about $73.80 per hour

Speed	Per second	Per hour
Standard	$0.0205	$73.80
Fast (lower latency, higher throughput)	$0.0410	$147.60

Includes the VideoRouter platform fee of 2.5% of provider cost.

Specs

KindReal-time edit of a live video stream

CreatorDecart

InputVideo

OutputLive video stream

Resolution720p

Max session600 s

Min session10 s

Speedsstandard, fast (options.speed)

How it works

Your server calls POST /v1/live-video/sessions with this model id. We check your key and credits, hold the cost of the session, and return a short-lived credential for the host.
Your browser or app streams from the host directly with that credential — the video never passes through our servers and the host API key never reaches the browser.
Your server sends a heartbeat while it runs and ends the session when the user leaves. You pay per second the session was live, up to 600 s per session.

Full reference, limits and errors: Live video & world models.

from videorouter_live import LiveVideo
lv = LiveVideo(api_key="llmr_sk_live_...")   # or set VIDEOROUTER_API_KEY

# On YOUR server: open a session, hand `connect` to the browser, settle on exit.
with lv.session(
    "decart/lucy-vton-3.6",
    max_duration_seconds=60,
    options={"speed": "standard"},
) as s:
    send_to_browser(s.connect)      # returned once; short-lived credential for the host
    wait_for_user_to_finish()
print(s.status, s.billed_seconds, s.cost_usd)

import { LiveVideo } from "videorouter-live";
const lv = new LiveVideo({ apiKey: process.env.VIDEOROUTER_API_KEY });

// On YOUR server: open a session, hand `connect` to the browser, settle in a finally.
const session = await lv.withSession(
  {
    model: "decart/lucy-vton-3.6",
    maxDurationSeconds: 60,
    options: {"speed": "standard"},
  },
  async (session) => {
    await sendToBrowser(session.connect);   // returned once
    await waitForUserToFinish();
    return session;
  },
);
console.log(session.status, session.billedSeconds, session.costUsd);

curl https://videorouter.sh/api/v1/live-video/sessions \
  -H "Authorization: Bearer llmr_sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{"model": "decart/lucy-vton-3.6", "max_duration_seconds": 60, "options": {"speed": "standard"}}'

# keep it alive while the user streams, then settle:
curl -X POST https://videorouter.sh/api/v1/live-video/sessions/$SESSION_ID/heartbeat -H "Authorization: Bearer llmr_sk_live_..."
curl -X POST https://videorouter.sh/api/v1/live-video/sessions/$SESSION_ID/end -H "Authorization: Bearer llmr_sk_live_..."

// `connect` is what your server got back from VideoRouter. connect.api_key is a short-lived Decart client
// token locked to this model — never ship your llmr_sk_ key to the browser.
import { createDecartClient, models } from "@decartai/sdk";

const client = createDecartClient({ apiKey: connect.api_key });
const model = models.realtime("lucy-vton-3.6");
const stream = await navigator.mediaDevices.getUserMedia({
  video: { frameRate: model.fps, width: model.width, height: model.height },
});
const rt = await client.realtime.connect(stream, {
  model,
  speed: "fast",                     // optional: 2x rate, lower latency
  onRemoteStream: (out) => { document.getElementById("output-video").srcObject = out; },
  initialState: { prompt: { text: "White ribbed turtleneck" } },   // or { image: garmentUrl }
});
// Change what it renders while live (set() replaces the whole state):
await rt.set({ prompt: "Red leather jacket", enhance: true });
// Call POST .../heartbeat on our API every ~5 s while it runs. Stop with rt.disconnect().