fal-ai/ltx-2.3/retake-video
LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.
Inference
Commercial use
Partner
Input
Hint: Drag and drop video files from your computer, video from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp4, mov, webm, m4v, gif
Logs
LTX-2.3 Retake Video
Regenerate and create new variations of existing video scenes with LTX-2.3 by Lightricks. Preserve the structural composition of a clip while generating fresh visual variations.
What's new in 2.3
- New VAE architecture for sharper fine details across retake variations
- Cleaner native audio regenerated alongside the new video
- Better prompt understanding for guiding retake direction
- Portrait 9:16 support in addition to landscape
- 24/48 FPS options for smoother motion
- LoRA fine-tuning support for custom styles and characters
Pricing
$0.10 per second of generated video. Pay-per-second, no minimums.
About LTX-2.3
LTX-2.3 is the latest open-source video generation model from Lightricks, built on a DiT-based architecture. It is released under the Apache 2.0 license, which permits commercial use and fine-tuning.