ltx2

Name: ltx2
Availability: InStock
Author: Calesthio

Generate video clips from text prompts or images using the LTX-2.3 22B DiT model.

46.2k|5.7k|Updated Mar 29, 2026

Search Tags:#video #generation #text-to-video #image-to-video #b-roll #ltx2

Ready to run

npx skills add https://github.com/calesthio/OpenMontage --skill ltx2

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ltx2
Source: https://github.com/calesthio/OpenMontage/tree/main/.agents/skills/ltx2
Command: npx skills add https://github.com/calesthio/OpenMontage --skill ltx2

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating high-quality video clips quickly by generating motion content from text prompts or reference images, reducing manual production time and enabling rapid concept-to-clip workflows.

Core Features & Use Cases

Text-to-video and image-to-video generation to produce short clips, motion sequences, and b-roll for editing.
Animated backgrounds and cinematic motion content to enrich narratives for promos, tutorials, and social content.
Real-world use cases include quick promo videos, social media assets, and concept visuals for storyboards.

Quick Start

Use the ltx2 tool to produce a ~5-second cinematic clip from a sunset prompt.

Frequently Asked Questions about ltx2

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate AI video clips from text prompts?▼

Text-to-video generation creates short motion sequences and b-roll by processing text prompts through the LTX-2.3 22B DiT model. You define width, height, frames, and seed parameters on a Modal deployment GPU endpoint to produce reproducible cinematic clips.

Can I create motion video from an existing image for b-roll?▼

Image-to-video generation animates existing reference images by processing them through the LTX-2.3 22B DiT model. This creates short motion sequences and cinematic clips suitable for marketing, tutorials, and social media b-roll.

Do I need a Modal deployment and GPU endpoint to run text-to-video generation?▼

Yes, running text-to-video generation requires a Modal deployment and a dedicated GPU endpoint. This infrastructure executes the LTX-2.3 22B DiT model to process prompt-driven parameters like width, height, frames, and seed for video production.

How do I ensure reproducible results when generating AI video clips?▼

To ensure reproducible AI video generation results, you define a specific seed parameter alongside width, height, and frame count. This locks the LTX-2.3 22B DiT model output, guaranteeing identical video clips across multiple generation runs.

What are the limitations of using AI video generation for marketing and social content?▼

AI video generation using the LTX-2.3 22B DiT model is limited to producing short assets, typically around 5-second cinematic clips. It requires a GPU endpoint and is best suited for b-roll, motion sequences, and concept visuals rather than long-form continuous video production.