skills.rest
artokun
artokunCOMMUNITY
Explore all skills by this author →
Website𝕏@artokunGitHub

ltxv2-video

Generate videos from text or images using the LTX-V2 19B model.

530|85|Updated Feb 15, 2026
Search Tags:#video generation#di#cinematic#text-to-video#image-to-video#ai video#ltxv2
One-click install
npx skills add https://github.com/artokun/comfyui-mcp --skill ltxv2-video
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ltxv2-video
Source: https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/ltxv2-video
Command: npx skills add https://github.com/artokun/comfyui-mcp --skill ltxv2-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables the creation of advanced video content using the LTX-V2 19B model, addressing the need for sophisticated text-to-video and image-to-video generation with fine-grained control.

Core Features & Use Cases

  • Text-to-Video (T2V): Generate videos from textual descriptions.
  • Image-to-Video (I2V): Transform existing images into dynamic video sequences.
  • Advanced Features: Supports distilled models for speed, two-stage upscaling for quality, and camera control LoRAs for cinematic movements.
  • Use Case: Create a short, cinematic clip of a futuristic cityscape by providing a detailed text prompt and leveraging camera control LoRAs for dynamic camera movements.

Quick Start

Use the ltxv2-video skill to generate a video from the prompt 'A majestic dragon soaring over a fantasy landscape at sunset'.

Frequently Asked Questions about ltxv2-video

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

FAQPage Schema
How do I generate high-fidelity AI video from text or images?▼

High-fidelity AI video generation involves using the LTX-V2 19B foundation model to process text-to-video and image-to-video inputs, producing dynamic cinematic sequences from your prompts.

Can I control camera movements when creating text-to-video content?▼

Camera control during text-to-video generation is achieved by loading specific camera control LoRAs, enabling precise cinematic camera movements within your generated video clips.

How do I upscale AI video generation outputs for better quality?▼

Upscaling AI video generation outputs uses a two-stage latent upscaling feature to enhance final video resolution and visual quality after the initial generation phase.

Do I need specific LoRAs to manage VRAM during video generation?▼

Specific model and LoRA loading is required for optimal VRAM management during video generation, ensuring the 19B foundation model runs efficiently without exceeding memory limits.

What is the best way to speed up text-to-video generation?▼

Speeding up text-to-video generation is best achieved by utilizing distilled models, which accelerate the rendering process while maintaining the core capabilities of the LTX-V2 19B model.

Related Skills

Explore More Design & Creative Skills→
artokunartokun
530

model-compatibility

Detail ComfyUI model compatibility requirements for SD 1.5, SDXL, Flux, SD3, and LTXV.

Community
Intermediate
xingBaGanxingBaGan

ltx2

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

Community
Intermediate
OSideMediaOSideMedia
275

higgsfield-image-shots

Generate cinematic still images with controlled shot framing, camera angles, and implied movements.

Community
Intermediate
ShopHeckShopHeck
1

ai-video-generation

Generate videos from text or images using multiple AI models via inference.sh CLI.

Community
Intermediate