Sign in Start free
Free

LightricksVideo

LTX 2.3

LTX 2.3: Lightricks' LTX 2.3: 1080p video from text or an image, with extendable clips.

Try LTX 2.3 View pricing

At a glance

LTX 2.3 by the numbers

  • 10 s Max length per generation
  • 1080P Max quality
  • Audio Sound generated with the picture
  • 2 Aspect ratios
  • 3 Ways to create
  • Lightricks Publisher

Use cases

What you can create with LTX 2.3

01

1080p with sound on a budget

Sharp clips with sound for a very low per-second cost.

02

Extend a video

Lengthen a clip by 5 to 10 seconds while keeping style, motion and sound.

03

Photographic shots

Precise 85 mm-style framing, shallow depth of field, crafted light.

04

Vertical and landscape

9:16 and 16:9 formats for social media and YouTube.

Overview

What is LTX 2.3?

LTX 2.3 is Lightricks’ open-source video model, released in March 2026 under the Apache 2.0 license (commercial use allowed). This version brings sharper details (textures, faces), cleaner native audio, better prompt understanding and vertical 9:16 support.

In Havincy, LTX 2.3 generates 6, 8 or 10 second clips in 1080p, from a text or an image, with sound. It can also extend a video by 5 to 10 seconds. Its very low price makes it the most affordable 1080p-with-sound model in the catalog.

  • Text or image to video
  • Extend existing clips
  • 1080p output
  • 6 to 10 s clips

LTX 2.3: specifications

Publisher
Lightricks
Generation modes
text → video, image → video, and video → video
Available durations
6, 8, 10 s
Resolutions
1080p
Aspect ratios
16:9, 9:16
Audio
Sound generated with the video
Available since
March 05, 2026
License
Commercial use allowed

The credit price depends on your settings and is shown before every generation.

Specs taken from the publisher’s public model page. See the documentation on fal.ai

Prompt examples

Prompts to try with LTX 2.3

  • A product reveal: a sleek watch rotating on a dark reflective surface

  • A drone shot gliding over a misty pine forest at sunrise

  • A chef flips a pancake in a sunlit kitchen, slow motion

Use cases

Compatible skills

Extend the video

Allonge un clip déjà généré : la scène continue après la dernière image, sans nouveau plan.

How it works

How to create with this model

  1. Describe the desired result in a Havincy conversation.
  2. Add a reference when the style, product, or character needs to be preserved.
  3. Generate, then ask for a variation or improvement without starting over.

FAQ

Frequently asked questions about LTX 2.3

Is LTX 2.3 open source?

Yes, Lightricks releases LTX 2.3 under the Apache 2.0 license, which allows commercial use and fine-tuning. In Havincy, you use it with no ComfyUI or GPU setup.

Does LTX 2.3 generate sound?

Yes, native audio is generated with the video and stays consistent when you extend a clip.

Which durations in Havincy?

6, 8 or 10 seconds per generation in 1080p, then extensions of 5, 8 or 10 seconds.

How much does LTX 2.3 cost in Havincy?

The credit price depends on the settings you pick (length, quality, sound, number of images) and is shown before every generation. See the Pricing page for details by plan.

A starting point for your next creation.

Explore the catalog

Seedance 2.5

Seedance 2.5: ByteDance's most advanced video model: text, image and multi-reference to video with native audio.

Kling 3.0 Pro

Kling 3.0 Pro: Kling's flagship: cinematic video from text or an image, with native audio and clips up to 15 s.

Veo 3.1

Veo 3.1: Google's Veo 3.1: realistic video with synchronized audio, from text or an image, and extendable clips.

Ready to create with LTX 2.3?

Describe your idea in Havincy, then refine the result in the conversation.

Create in Havincy