Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
Available now on ModelsLab · Video Generation

LTX 2.3 Pro Image To VideoImages Into Cinematic Videos

Try LTX 2.3 Pro Image To VideoAPI Documentation

Unlock Pro Video Generation

High Fidelity

Pro Quality Output

LTX 2.3 Pro Image To Video delivers sharper details and better prompt adherence than Fast variant.

Synchronized Audio

Native Audio Generation

Generates motion and audio in one pass using improved HiFi-GAN vocoder for clean sound.

Flexible Controls

Portrait and Motion

Supports 9:16 portrait, camera motions, end frame interpolation, up to 4K and 20s duration.

Examples

See what LTX 2.3 Pro Image To Video can create

Copy any prompt below and try it yourself in the playground.

Urban Timelapse

“Start with a bustling city skyline at dusk, camera slowly dollies in as lights flicker on, smooth 24fps motion, cinematic lighting, high detail architecture.”

Ocean Waves

“Serene beach scene with turquoise waves crashing on sand, gentle camera pan right, realistic water physics, 25fps, golden hour sunlight.”

Mountain Aerial

“Snow-capped peaks under clear sky, jib up from valley floor revealing panorama, crisp details on rocks and trees, 4K resolution.”

Abstract Lights

“Neon light trails in dark void, focus shift from blur to sharp patterns, fluid motion at 50fps, vibrant colors, futuristic style.”

For Developers

A few lines of code.
Video from image. Few lines.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/image-to-video",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "In the image girl singing a melody song waving her wooden blow her hair lighting waving",
  "duration": "6",
  "init_image": "https://assets.modelslab.ai/generations/79dae226-a403-47ae-af9e-f46b09846435.webp"
}
)
print(response.json())

FAQ

Common questions about LTX 2.3 Pro Image To Video

Read the docs

LTX 2.3 Pro Image To Video is the high-fidelity model from Lightricks for generating videos from images. It includes audio-to-video, retake, and extend features. Supports up to 4K and 20 seconds.

Send image and prompt to LTX 2.3 Pro Image To Video API endpoint. Optional end frame for interpolation. Returns MP4 with synchronized audio.

Supports 1080p, 1440p, 4K at 16:9 or 9:16 aspect ratios. Frame rates: 24, 25, 48, 50 FPS.

LTX 2.3 Pro Image To Video excels in fidelity and audio sync over prior versions. Use for pro workflows needing consistent motion and sound.

Yes, native 9:16 portrait support up to 1080x1920. Ideal for mobile and vertical content.

Required: start image. Optional: end frame image, prompt for motion. Supports PNG, JPEG, WebP formats.

Ready to create?

Start generating with LTX 2.3 Pro Image To Video on ModelsLab.

Try LTX 2.3 Pro Image To VideoAPI Documentation