MiniMax H3 Open Weights | Try in Video Generator →

LTX 2 19B Control | AI Motion Control Video API

wavespeed-ai/

LTX-2 19B ControlNet generates synchronized audio-video (up to 20s) from video input with pose, depth, or canny edge guidance. Supports audio preservation, generation, or removal for flexible video transformation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

motion-control
Input

Idle

$0.2per run·~50 / $10

ExamplesView all

Related Models

README

LTX-2 19B ControlNet

LTX-2 ControlNet is a video-to-video transformation model that applies pose, depth, or edge guidance to generate new video content while preserving motion structure from the input. Built on the 19B DiT architecture, it supports synchronized audio handling with options to preserve original audio, generate new audio, or output silent video.

Why Choose This?

  • ControlNet guidance modes Choose from pose, depth, or canny edge detection to guide video generation while preserving motion structure.

  • Flexible audio handling Preserve original audio, generate new synchronized audio, or create silent output.

  • High-fidelity output Leverages the 19B-parameter DiT architecture for detailed, temporally consistent video.

  • Character-driven transformation Use a reference image to drive the appearance while the input video controls motion.

  • Prompt Enhancer Built-in tool to automatically improve your prompts for better results.

Parameters

ParameterRequiredDescription
videoYesInput video providing motion and structure
imageNoReference image for appearance guidance
promptNoText description of desired output
modeNoControl mode: pose (default), depth, or canny
audio_modeNoAudio handling: preserve (default), generate, or none
resolutionNoOutput resolution: 480p, 720p (default), or 1080p
seedNoRandom seed for reproducibility (-1 for random)

Control Modes

ModeDescription
poseSkeleton/pose guidance for human motion (default)
depthDepth map guidance for scene structure
cannyEdge detection guidance for shape preservation

Audio Modes

ModeDescription
preserveKeep original audio from input video (default)
generateCreate new synchronized audio
noneOutput video without audio

How to Use

  1. Upload your video — the input video providing motion structure.
  2. Upload your image (optional) — reference image that defines appearance.
  3. Write your prompt — describe the desired transformation.
  4. Select control mode — pose, depth, or canny based on your needs.
  5. Select audio mode — preserve, generate, or none.
  6. Set resolution — 480p for speed, 720p for balance, 1080p for quality.
  7. Run — submit and download the transformed video.

Pricing

Resolution5s10s15s20s (max)
480p$0.15$0.30$0.45$0.60
720p$0.20$0.40$0.60$0.80
1080p$0.30$0.60$0.90$1.20

Billing Rules

  • Base price: $0.20 (720p, 5 seconds)
  • Resolution multiplier: 480p = 0.75×, 720p = 1×, 1080p = 1.5×
  • Minimum charge: 5 seconds
  • Maximum billed duration: 20 seconds
  • Total cost = (duration / 5) × $0.20 × resolution_multiplier

Best Use Cases

  • Character Animation — Animate a character image with motion from reference video.
  • Style Transfer — Apply a reference style to existing video content.
  • Motion Preservation — Maintain motion structure while changing appearance.
  • Video Editing — Transform video subjects while keeping movement.
  • Dance Transfer — Apply dance moves to different characters.

Pro Tips

  • Match the subject pose in your image to the starting pose in the video.
  • Use pose mode for human/character motion, depth for scene structure, canny for edge-based guidance.
  • Preserve audio for lip-sync scenarios, generate for new content.
  • Iterate at 480p, then render final at 720p or 1080p.

Notes

  • Maximum video duration is 20 seconds per job.
  • Videos shorter than 5 seconds are billed as 5 seconds.
  • For best results, ensure the reference image matches the subject type in the video.

Related Models

Note:This website uses AI models provided by third parties.

Ltx 2 19b Control API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/control with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ltx 2 19b Control below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "mode": "pose",
    "audio_mode": "preserve",
    "resolution": "720p",
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/control" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/control";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "mode": "pose",
        "audio_mode": "preserve",
        "resolution": "720p",
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "mode": "pose",
    "audio_mode": "preserve",
    "resolution": "720p",
    "seed": -1
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/control", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Ltx 2 19b Control API — Frequently asked questions

What is the Ltx 2 19b Control API?

Ltx 2 19b Control is a WaveSpeedAI model for pose / motion driven video, exposed as a REST API on WaveSpeedAI. LTX-2 19B ControlNet generates synchronized audio-video (up to 20s) from video input with pose, depth, or canny edge guidance. Supports audio preservation, generation, or removal for flexible video transformation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Ltx 2 19b Control 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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ltx-2-19b-control.

How much does Ltx 2 19b Control cost per run?

Ltx 2 19b Control 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 Ltx 2 19b Control accept?

Key inputs: `prompt`, `image`, `video`, `resolution`, `seed`, `audio_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/wavespeed-ai/ltx-2-19b-control.

How do I get started with the Ltx 2 19b Control 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 Ltx 2 19b Control outputs commercially?

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