LTX Video Generation Models
Production-ready AI video generation built for control, quality, and real-world workflows.
.svg)
Built for real video production
LTX video generation models are designed for creating and editing video with precision and control. From generating video from text, images, or audio to non-destructive AI video editing, LTX supports scalable workflows for production, post-production, and experimentation.
All LTX models share a common design philosophy: composability, predictability, and production readiness.
Video generation capabilities
Use LTX models across multiple video generation and editing workflows.
Text to Video
Generate cinematic video directly from text prompts. Control motion, composition, and visual flow using natural language.
Image to Video
Animate still images into coherent video. Preserve visual identity while adding motion, transitions, and cinematic depth.
Video to Video
Edit and transform videos with precise control — refine scenes, enhance quality, and adjust motion while preserving continuity and character consistency.
Audio to Video
Generate video directly from audio, where sound drives motion, timing, and scene structure. Ideal for music, voice, and audio-led storytelling.
Our video generation models
Choose the model that fits your workflow, quality requirements, and level of creative control.
LTX-2
LTX-2 is the flagship video generation model, built for high-fidelity creation and directable AI video editing. It supports synchronized audio and video generation and advanced editing workflows like LTX Retake.
Key highlights:
- Directable video editing with LTX Retake
- High-quality, production-ready output
- Designed for creative iteration and post-production
LTXV
LTXV is the foundational open video generation model in the LTX ecosystem. It introduced long-form generation, keyframes, and advanced conditioning, and remains a powerful option for structured video creation and research.
Technical characteristics:
- Open-source video generation
- Long-form and keyframe-based workflows
- Strong control for experimentation and pipelines
Built for AI Video Production
One ecosystem, multiple video workflows
LTX video generation models are designed to work together as a unified system. Start with any generation mode — text, image, audio, or video — and combine capabilities across models to build end-to-end video workflows for creation, editing, and post-production. Generate video from text or images, refine it with Video to Video editing, and iterate without switching tools — all within the LTX ecosystem.
Personas
Subtext goes here enables true audio-to-video AI generation without relying on text-first pipelines.
Product integrators
Embed video generation into existing platforms with minimal engineering overhead. Reliable API, predictable performance, easy integration.
Visionaries & custom builders
Build and fine-tune video products on a stable foundation. High-fidelity outputs and long-term model stability for vertical AI solutions.
.webp)
Enterprise Content Platforms
Transform voice, music, and sound into high-quality video for campaigns, education, and distribution pipelines.
.jpeg)
Research & Academia
Experiment with audio-driven animation, timing alignment, and audio-visual generation using a controllable video model.
Persona 5
Experiment with audio-driven animation, timing alignment, and audio-visual generation using a controllable video model.
Persona 6
Experiment with audio-driven animation, timing alignment, and audio-visual generation using a controllable video model.
Persona 7
Experiment with audio-driven animation, timing alignment, and audio-visual generation using a controllable video model.
Persona 8
Experiment with audio-driven animation, timing alignment, and audio-visual generation using a controllable video model.
LTX-2 API pricing
Usage-based pricing by endpoint and output quality.
Text-to-Video
FastDesigned for quick iteration, previews, and fast creative exploration.
/v1/text-to-videoPricing:- 1920×1080 — $0.04/sec
- 2560×1440 — $0.08/sec
- 3840×2160 (4K) — $0.16/sec
Notes:- Same pricing applies for text input and pure prompt -based generation.
Text-to-Video
ProOptimized for higher fidelity and increased temporal stability. Best for production-ready output and final renders.
/v1/text-to-videoPricing:- 1920×1080 — $0.06/sec
- 2560×1440 — $0.12/sec
- 3840×2160 (4K) — $0.24/sec
Notes:- Deal for client-facing content or polished deliverables.
- Higher compute level → higher visual quality.
Image-to-Video
FastDesigned for quick iteration, previews, and fast creative exploration.
/v1/image-to-videoPricing:- 1920×1080 — $0.04/sec
- 2560×1440 — $0.08/sec
- 3840×2160 (4K) — $0.16/sec
Notes:- Same compute cost as text-to-video Fast.
- Resolution and duration determine total cost.
Image-to-Video
ProFor detailed, stable motion derived from a still image. Best for high-quality sequences, storytelling, and production use.
/v1/text-to-videoPricing:- 1920×1080 — $0.06/sec
- 2560×1440 — $0.12/sec
- 3840×2160 (4K) — $0.24/sec
Notes:- Uses the Pro rendering path for maximum fidelity.
- Ideal when visual consistency is critical.
Retake - video editing
ProRefine only the parts that need adjustment - no need to regenerate the whole video. Perfect for fixing scenes, adjusting elements, or improving localized areas.
/v1/retakePricing:- 1920×1080 — $0.10/sec
Notes:- Currently available in 1080p only.
- Billed per second of input video.
Audio to Video (A2V)
ProGenerate video directly from audio — where voice, music, and sound define structure, pacing, and motion.
/v1/audio-to-videoPricing:- 1920×1080 — $0.10/sec
Supported inputs:- Audio: WAV, MP3, M4A, OGG
- Image (optional): PNG, JPEG, WEBP
Notes:- Billed per second of input audio.
- Generates up to ~20seconds per request
- Full-length videos can be created by chaining multiple requests
- Currently available in 1080p only
About LTX Models
LTX builds state-of-the-art generative AI models designed for real-world deployment. Our models prioritize control, composability, and performance — enabling developers and platforms to build production-ready AI video experiences.
FAQs
What is the LTX video generation?
LTX video generation is a unified ecosystem of AI models designed for creating, editing, and transforming video. It supports workflows such as Text to Video, Image to Video, Audio to Video, and Video to Video editing with LTX Retake.
What’s the difference between LTX models and video generation capabilities?
Models (such as LTX-2 and LTXV) are the underlying engines that power video generation.
Capabilities describe how those models are used in practice, such as generating video from text or editing existing video.
Which LTX model should I start with?
- LTX-2 is the flagship model, ideal for high-quality generation and directable video editing with LTX Retake.
- LTXV is the foundational open model, suited for long-form generation, control, and experimentation.
Are LTX video generation models production-ready?
Yes. LTX models are built for real-world production workflows, emphasizing control, composability, and scalable deployment.
Can I combine different video generation workflows?
Yes. LTX models are designed as a single ecosystem. You can generate video from text, images, or audio, then refine and edit it using Video to Video workflows like LTX Retake.
