LTX-2.3Sharp. Fast. Open Source.
Open Source. Production Ready.
Sharper Fine Details Than Ever
LTX-2.3 introduces a new VAE that produces noticeably sharper output. Textures, facial features, and small objects retain clarity across the full frame. The improvement is especially visible at higher resolutions where previous versions softened details.
Cleaner Sound, Built In
Generate audio natively alongside video with improved clarity in 2.3. Sound effects, ambient noise, and dialogue are synchronized from generation. A dedicated audio-to-video endpoint lets you provide an audio clip and generate matching visuals.
Every Mode You Need
Text-to-video, image-to-video, audio-to-video, extend, and retake. Fast variants for text-to-video and image-to-video when speed matters. Portrait 9:16 support, 24/48 FPS options, and LoRA fine-tuning across the board.
Seven endpoints, one model
Generate video from text, images, or audio. Extend existing clips or retake scenes. Fast variants available for text-to-video and image-to-video.
See what LTX-2.3 can create
Copy any prompt below and try it yourself in the playground.
"Snorkel lens ground-scraping tracking shot following a barefoot Ethiopian long-distance runner training on a dirt road at dawn, camera inches from the ground racing alongside, her feet kicking up red dust in slow motion at 240fps, Rift Valley landscape blurred in the background, the texture of earth and callused skin in hyper-detail, 40mm snorkel lens at ground height, Nike Running documentary meets Lubezki natural light, the poetry of human endurance"
"Drone descent through the open oculus of a derelict Soviet-era radio telescope dish, spiraling downward into the rusted parabolic bowl where a lone botanist catalogs wildflowers growing through cracked concrete, her red jacket the only color against oxidized metal and grey sky, 24mm on a caged FPV drone, the descent creating a vertigo spiral, Tarkovsky Stalker zones of alien beauty reclaiming technology, science swallowed by nature"
"Through-the-veil shot of a bride's face during an Indian wedding ceremony, camera positioned behind the sheer red dupatta fabric, the embroidered pattern creating a textured overlay on her face, her eyes lined with kohl looking down at henna-covered hands, marigold garlands in soft background bokeh, 85mm f/1.2 focused through the fabric layer, warm tungsten and candlelight, Mira Nair Monsoon Wedding intimacy"
"A woman whispering into the microphone"
Common questions about LTX-2.3
What is LTX-2.3?
LTX-2.3 is the latest open-source video generation model from Lightricks. It uses a DiT-based architecture with a new VAE for sharper fine details, native audio generation, and support for up to 20-second clips at 4K resolution. It is available under the Apache 2.0 license.
What's new in LTX-2.3 compared to previous versions?
LTX-2.3 introduces a new VAE for sharper fine details, cleaner audio generation, stronger image-to-video quality, better prompt understanding, last-frame interpolation, portrait 9:16 support, and 24/48 FPS options.
What endpoints are available?
LTX-2.3 offers seven endpoints: text-to-video, image-to-video, audio-to-video, extend-video, and retake-video. Text-to-video and image-to-video also have fast variants optimized for speed.
How long can generated videos be?
LTX-2.3 generates videos up to 20 seconds in a single generation. You can extend clips further using the dedicated extend-video endpoint.
Does LTX-2.3 support audio?
Yes. LTX-2.3 generates native audio alongside video. The 2.3 release brings cleaner audio quality compared to previous versions. There is also a dedicated audio-to-video endpoint where you provide an audio clip and the model generates matching video.
Can I fine-tune LTX-2.3?
Yes. LTX-2.3 supports LoRA fine-tuning, allowing you to customize the model for specific styles, characters, or use cases. This is available because LTX is fully open source under the Apache 2.0 license.
How do I get started with the API?
Install the fal.ai SDK (Python or JavaScript), grab an API key from your dashboard, and make your first request in three lines of code. The API is serverless, so no GPUs to manage, no infrastructure to set up. Check the API documentation for all available parameters.
How much does LTX-2.3 cost on fal.ai?
Pay-per-second with no minimums. Text-to-video and image-to-video start at $0.06/s (1080p), $0.12/s (1440p), or $0.24/s (2160p). Fast variants start at $0.04/s (1080p), $0.08/s (1440p), or $0.16/s (2160p). Audio-to-video, extend-video, and retake-video are $0.10/s.
Can I use LTX-2.3 for commercial projects?
LTX-2.3 is released under the Apache 2.0 license, which permits commercial use. Check fal.ai's terms of service for additional details on usage through the platform.