LTX-2 is the first DiT-based audio-video foundation model with synchronized audio and video output. It generates high-fidelity videos from text prompts or images with native audio-visual synthesis in a single process.
Current account balance
—
Wan 2.6 115
High-quality video generation with text, image, and video input support
0/5000
duration
resolution
share_publicly
share_tip
LTX-2 AI Video Generator - Create Professional Videos from Text and Images
Why Choose LTX-2
Experience the next generation of AI video creation with the first DiT-based audio-video foundation model
Synchronized Audio-Video
Generate videos with perfectly synchronized audio and visuals in a single process. No need for separate audio generation.
High-Fidelity Output
Create stunning videos up to 1080p resolution with exceptional clarity, smooth motion at 50 FPS, and lifelike details.
Flexible Duration
Generate videos from 5 to 20 seconds with consistent quality. Perfect for social media, ads, and creative projects.
Powerful API
Seamlessly integrate video generation into your applications with our comprehensive REST API. Full documentation available.
Multiple Aspect Ratios
Support for 16:9 landscape and 9:16 portrait formats. Choose resolutions from 480p to 1080p for any use case.
Commercial Ready
All generated content is fully licensed for commercial use. Build products, create marketing content, and monetize freely.
Frequently Asked Questions
Find answers to common questions about LTX-2
Frequently asked questions
Ready to Create Amazing Videos?
Start generating professional AI videos today. No credit card required for free tier.