LTX 2.3
ltx23.app
Generate AI videos online from text, images, or audio with LTX 2.3. Fast open-source video generation for everyone.
Description
LTX 2.3 is an AI-powered video generation platform that enables users to create videos from text, images, or audio inputs. Built on the Diffusion Transformer architecture with 22 billion parameters, it offers fast and high-quality video generation. The platform caters to creators of all levels, providing tools for generating cinematic scenes, product demos, and social media content. Features include multi-modal generation pipeline, native portrait video, and open-source accessibility, making it a versatile and cost-effective video creation solution.
Installation
Not sure where to start — ask an assistant to walk you through:
Features
🚀 Text-to-Video Generation
Describe any scene and LTX 2.3 generates cinematic video with fluid motion, accurate lighting, and natural physics. Users can quickly transform textual ideas into compelling visual content, saving time and resources in v
🔎 Image-to-Video Transformation
Upload a reference image and LTX 2.3 transforms it into a dynamic video clip with smooth camera motion and lifelike animation. This feature allows users to animate static images, creating engaging content for marketing o
🛠️ Audio-to-Video Synchronization
Feed an audio track and LTX 2.3 generates matching video with tight lip-sync, beat-aligned motion, and spatial audio cues. This feature allows users to effortlessly create music videos, podcasts, and other audio-visual c
Use cases
Generate social media video ads.
Create animated explainers from text.
Turn product photos into demo videos.
Sync music with AI generated visuals.
Animate a brand's marketing storyboard.
FAQ
LTX 2.3 is a 22-billion-parameter open-source AI video model built by Lightricks on the Diffusion Transformer (DiT) architecture.
No. On ltx23.app all rendering happens in the cloud — no local GPU, VRAM, or desktop installation required.
On H100 GPUs, the LTX 2 series achieves roughly 18x the throughput of WAN 2.2 14B, making it significantly faster for batch rendering.
Videos render at up to 1080p HD in 16:9, 9:16, 1:1, and 4:3 aspect ratios with durations from 4 to 20 seconds.
Yes. New accounts on ltx23.app receive free credits to try AI video generation.
Yes. Videos generated on ltx23.app include full commercial rights.
LTX 2.3 is available as a base checkpoint, distilled checkpoint with LoRA, FP8 scaled variant, and GGUF quantized format.
Create a free account on ltx23.app, enter a text prompt describing your video, optionally upload a reference image or audio then generate.
Key features include text-to-video, image-to-video, audio-to-video generation, native portrait output, rebuilt VAE, and commercial licensing.
LTX 2.3 leverages audio-to-video synchronization with tight lip-sync, beat-aligned motion, and spatial audio cues.
Specs
| Type | Tool |
| Section | Video Generation |
| Pricing | paid (от $19.9/mo) |
| Platform | Web only |
| Systems | web |
| Hosting | cloud |
| Install | saas |
| Site language | en |
| Vendor | emily_jone92387 |
| Launched | 2026-03-21 |