Ready to generate your own videos with simple text prompts? 🎬 Learn how to use @ComfyUI and the @ltx_model LTX-2 optimized model on your RTX AI PC with this educational guide linked below.
LTX-2 Text and Image to Video Generation Model
Built by Lightricks, LTX-2 is a production-ready AI creative engine that outputs cinematic 1080p videos complete with synchronized native audio. It offers Pro and Fast modes for text-to-video and image-to-video generation, plus a purpose-built Retake mode for precise, targeted video edits. Craft professional videos with smooth motion, consistent lighting, and accurate lip-sync that works perfectly for ads, social media content, and professional production workflows.
Public
Generate Audio
Sample LTX-2 Text-to-Video Creations
Browse cinematic videos generated from text prompts using LTX-2's Pro and Fast generation modes. Spanning everything from sweeping epic fantasy to tense sci-fi horror, see for yourself how plain text descriptions turn into breathtaking 1080p videos complete with fully synchronized native audio.
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
AI Video
Floating City Arrival
A sweeping epic fantasy opening shot, featuring a detailed ornate airship pushing through thick cloud cover, on course for a massive floating city linked together by glowing energy bridges.
Prompt
“Stunning wide opening establishing shot. A grand, intricately designed airship drifts slowly out of thick cloud cover, nearing an impossibly large massive city that floats high among the clouds, connected by glowing energy bridges.”
LTX-2 Image-to-Video Showcase
Turn any static still image into a smooth, dynamic 1080p video complete with perfectly synchronized audio. Browse these examples to see how LTX-2 breathes life into static scenes, from pulse-pounding chase sequences to grand epic fantasy duels, all with seamless natural motion.
Input
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Output
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
Harry Potter Epic Duel
Example Video Edits for LTX-2 Retake
Make targeted changes to any segment of your video by retaking just that part: swap visuals, update audio, or edit both while keeping your original timing and scene continuity intact. It’s ideal for refining individual moments without having to regenerate your entire video from start to finish.
Input
Video
Video
Video
Video
Video
Output
AI Generated
AI Generated
AI Generated
AI Generated
AI Generated
Day to Night Transformation
LTX-2 YouTube Videos
Watch demonstrations and tutorials of LTX-2, the first open-source audio-video generation model
LTX-2 Popular Reviews on X
See what the AI community is saying about LTX-2, the first open-source audio-video generation model
🚀 LTX-2 is now open source: text → audio + video. Today we’re releasing LTX-2, the first open-source foundation model for joint audiovisual generation, together with a full technical report. 🧵👇
LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Show more
The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.
AI video shouldn’t be locked behind closed systems. We’re releasing LTX-2 as a truly open-source AI video model. Here’s @ZeevFarbman (CEO & Co-Founder, Lightricks) on why openness, local access, and community matter. 🧵
LTX-2 by @Lightricks: Open-source • Native 4K video at up to 50 FPS • High-quality long-form video with strong temporal consistency • Audio-conditioned generation with motion synced to sound • Fine-grained camera & motion control • Efficient enough to run on consumer GPUs Show more
We partnered with @NVIDIA_AI_PC and @Lightricks to push local AI video forward. NVFP4 and NVFP8 checkpoints are now available for LTX-2. With NVIDIA-optimized ComfyUI, LTX-2 delivers cloud-class 4K video locally - up to 3X faster with 60% less VRAM using NVFP4. Show more
LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control -
What is LTX-2?
Lightricks' production-grade video AI model with synchronized native audio generation
1080pFull HD Resolution
6-20 secondsVideo Duration Range
3 ModesPro, Fast & Retake
Native AudioSynchronized Sound
First open-source model to achieve cinematic 1080p video with contextually appropriate audio in a unified system.
1080pFull HD Resolution
6-20 secondsVideo Duration Range
3 ModesPro, Fast & Retake
Native AudioSynchronized Sound
What is LTX-2?
Lightricks' production-grade video AI model with synchronized native audio generation
First open-source model to achieve cinematic 1080p video with contextually appropriate audio in a unified system.
LTX-2 Features
Unlock the industry-leading capabilities of Lightricks LTX-2 built for modern professional video production
Synchronized Native Audio
Create stunning cinematic videos with automatically synced native audio that aligns flawlessly with every visual beat. LTX-2 builds immersive, engaging soundscapes complete with dialogue and accurate lip-sync, perfect for professional ads and social media content.
Pro & Fast Modes
Pick the mode that fits your workflow: Pro mode delivers maximum-quality 1080p output, while Fast mode lets you iterate quickly on content up to 20 seconds long. Both modes produce production-ready results tailored to fit your unique project needs.
Text-to-Video Generation
Turn your text prompts into polished cinematic 1080p videos featuring smooth, lifelike motion and consistent, natural lighting. Build professional-grade video content directly from your descriptions, with flexible duration options ranging from 6 to 20 seconds.
Image-to-Video Animation
Animate your static still images with natural, believable motion and perfectly synchronized audio. LTX-2 preserves your original image composition and artistic style, adding dynamic movement that feels authentic and hooks viewers.
Video Retake Mode
Make targeted changes to any section of your video with retake mode, swapping out visuals, audio, or both while keeping your original timing and scene continuity intact. It’s ideal for iterative refinement and creative experimentation, no full regeneration required.
Production-Ready Quality
Export 1080p high-definition videos that are ready for immediate professional use across advertising campaigns, social media platforms, and commercial content production. Enjoy consistent, reliable quality with realistic motion physics and natural, balanced lighting.
Flexible Duration Control
Generate custom-length videos from 6 to 20 seconds, with granular, precise control over your project timing. Pro mode offers 6-10 second output for premium quality clips, while Fast mode supports up to 20 seconds for longer-form content.
Multi-Modal Capabilities
Three powerful production modes are packed into one core engine: text-to-video for fast concept creation, image-to-video for custom animation, and retake mode for fine-tuning your final clip. It’s a complete, all-in-one toolkit for end-to-end professional video production workflows.
Frequently Asked Questions
Still have questions?
LTX-2 Pro mode produces top-tier cinematic video quality at a rate of 6 credits per second, and is available for clip durations of 6, 8, or 10 seconds. Fast mode is built for faster generation and lower cost per second at 4 credits, and supports flexible custom durations between 6 and 20 seconds. Both output 1080p resolution videos with fully synchronized native audio.
Yes, synchronized native audio is generated by default for every video output from LTX-2. This audio includes matching ambient background sounds, sound effects, and other audio that aligns perfectly with your video's visuals. You can turn off automatic audio generation if you want a silent video or plan to add your own custom audio track after generation.
Retake mode lets you make targeted edits to specific parts of an existing video you've already generated. You can swap out just the visuals, just the audio, or both at once, while keeping the original clip's timing and overall continuity intact. It's ideal for fine-tuning specific moments without having to regenerate your entire full video. You're only billed for the actual duration of the section you retake, with a maximum cap of 16 seconds.
Absolutely. LTX-2 supports both text-to-video and image-to-video generation in both Pro and Fast modes. Text-to-video builds full videos entirely from your written prompts, while image-to-video turns your static input images into dynamic moving video content complete with motion and matching audio.
LTX-2 outputs cinematic quality videos at 1080p (Full HD) resolution. All generated videos use the MP4 file format, which works seamlessly across every major platform and device. For image-to-video, we accept JPG, PNG, and WEBP input files up to 10MB in size.
Pricing is calculated based on the total duration of your generated video: Fast mode costs 4 credits per second, Pro mode costs 6 credits per second, and Retake mode costs 10 credits per second. For Retake mode, billing only applies to the actual duration of the clip you edit, with a maximum 16-second cap. Credits are only deducted after your video generation completes successfully.
How to Use LTX-2 Text-to-Video
1
Choose Your Mode2
Write Your Prompt3
Generate and RefinePick between two work modes matched to your current goal: Pro mode delivers top-tier cinematic quality for 6-10 second clips at 6 credits per second, while Fast mode enables fast, low-cost experimentation and supports 6-20 second clips at 4 credits per second. Use Pro mode when building finished production assets, and reach for Fast mode when brainstorming concepts or testing draft ideas.
Step-by-Step Guide to Using LTX-2 Image-to-Video
1
Upload Your Image2
Describe the Animation3
Animate and ExportBegin by uploading your high-quality still image, accepted formats include JPG, PNG, and WEBP with a maximum file size of 10MB. For best results, choose an image with sharp composition and even, good lighting. Next, select your preferred workflow: Pro mode delivers cinema-grade output for 6-10 second clips at 6 credits per second, while Fast mode offers rapid 6-20 second turnarounds at 4 credits per second.
Flexible AI Pricing
Pay-as-you-go credits or subscription plans. No hidden fees, cancel anytime.