LTX-Video

LTX-Video

This is the official repository for LTX-Video.

🚀 New: LTX-2 is Now Available!

We're excited to announce LTX-2 - the next generation of LTX with synchronized audio+video generation!

LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model. LTX-2 is now the primary home for LTX development and includes significant improvements:

- 🎵 Synchronized Audio+Video Generation - Generate videos with perfectly synchronized audio
- 🎬 Latest Model - LTX-2 with improved quality and capabilities
- 🔌 ComfyUI Integration - Built into ComfyUI core for seamless workflows
- 🎯 Advanced Features:
  - Multiple keyframe support
  - IC-LoRA control models for precise generation
  - Standard LoRA support for style customization
  - Latent upsampler for multiscale pipelines
- 🛠️ Training Tools - LoRA training capabilities
- 📚 Comprehensive Documentation - Full documentation at https://docs.ltx.video
- 🔄 Active Development - Ongoing improvements and community support

👉 Check out LTX-2 here

📖 View Documentation

Table of Contents

- Introduction
- What's New
- Models
- Quick Start Guide
  - Online demo
  - Run locally
    - Installation
    - Inference
  - ComfyUI Integration
  - Diffusers Integration
- Model User Guide
- Community Contribution
- Training
- Control Models
- Join Us!
- Acknowledgement

Introduction

LTX-Video is the first DiT-based video generation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access. It can generate up to 50 FPS videos at native 4K resolution with synchronized audio in one pass.
The model is trained on a large-scale dataset of diverse videos and can generate high-resolution videos with realistic and diverse content.

The model supports image-to-video, multi-keyframe conditioning, keyframe-based animation, video extension (both forward and backward), video-to-video transformations, and any combination of these features.

Image-to-video examples

Controlled video examples

News

October 23, 2025: LTX-2 Announced

Today we announced our newest foundation model, LTX-2. LTX-2 represents a major leap forward from our previous model, LTXV 0.9.8. Here’s what’s new:
* Audio + Video, Together: Visuals and sound are generated in one coherent process, with motion, dialogue, ambience, and music flowing simultaneously.
* 4K Fidelity: Professional-grade precision with native 4K and up to 50 fps, sharp textures, clean motion, and synchronized audio.
* Longer Generations: LTX-2 supports longer, continuous clips with synchronized audio up to 10 seconds.
* Low Cost & Efficiency: Up to 50% lower compute cost than competing models, powered by a multi-GPU inference stack.
* Creative Control: Multi-keyframe conditioning, 3D camera logic, and LoRA fine-tuning deliver frame-level precision and style consistency.

For more details, please see our blog post. LTX-2 model weights, code, and benchmarks will be released to the community later in 2025. 

July, 16th, 2025: New Distilled models v0.9.8 with up to 60 s

……（后略，见原文）