LTX 2.3

Text-to-Video Generation

Converts natural language prompts into cinematic videos with accurate lighting, fluid motion, and realistic physics.

Image-to-Video Conversion

Transforms uploaded images into dynamic video clips featuring smooth camera movement and lifelike animation.

Audio-to-Video Synchronization

Generates videos synchronized with audio tracks, including lip-sync, beat-aligned motion, and spatial audio cues.

Multi-Modal Video Generation

Supports text, image, audio, and video inputs for versatile content creation through a unified platform.

Native Portrait Video Output

Creates vertical videos at 1080x1920 resolution, optimized for platforms like TikTok, Reels, and Shorts.

22B-Parameter DiT Engine

Utilizes a 22-billion-parameter Diffusion Transformer architecture for superior detail, texture, and edge quality.

Expanded Text Connector

Features a 4x-larger text connector for precise interpretation of complex prompts, including spatial layout and mood.

Face & Character Preservation

Maintains consistent facial features, expressions, and body proportions across video frames for storytelling.

Rebuilt VAE for Sharper Output

Implements a reworked VAE and latent space for crisper hair, cleaner edges, and enhanced texture preservation.

Open-Source & Commercial Licensing

Offers open-source weights on Hugging Face with free commercial use under 10M annual revenue for qualifying organizations.

• Social media marketers: Create engaging vertical video content for TikTok and Instagram Reels using LTX 2.3's native portrait video generation.
• E-commerce businesses: Generate product demo videos at scale from product images, reducing production costs and time.
• Game developers: Produce cinematic trailers and in-game cutscenes using LTX 2.3's text-to-video and image-to-video features.
• Content creators: Transform storyboard frames into cinema-grade animations with smooth motion and continuity.
• Advertising agencies: Generate localized video ads for multiple markets quickly with LTX 2.3's audio-to-video synchronization.

What is LTX 2.3?

LTX 2.3 is a 22-billion-parameter open-source AI video model built by Lightricks on the Diffusion Transformer (DiT) architecture. It supports text-to-video, image-to-video, audio-to-video, and video-to-video generation with native portrait output, rebuilt VAE, and a 4x-expanded text connector for more accurate prompt interpretation. Model weights are available on Hugging Face for both dev and distilled checkpoints.

Do I need a powerful GPU or local desktop setup?

No. On ltx23.app all rendering happens in the cloud — no local GPU, VRAM, or desktop installation required. If you prefer running locally, LTX 2.3 supports ComfyUI workflows and GGUF/FP8 quantized formats for lower hardware requirements. The recommended local setup is an NVIDIA GPU with 32 GB+ VRAM, 32 GB RAM, and 60 GB storage on Windows.

How does LTX 2.3 compare to other video models like WAN 2.2?

On H100 GPUs, the LTX 2 series achieves roughly 18x the throughput of WAN 2.2 14B, making it significantly faster for batch rendering. LTX 2.3 also introduces native 9:16 portrait video, a reworked audio vocoder, and sharper edge detail from its rebuilt latent space — improvements not yet matched by most competing open-source models.

What video specs does the model support?

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 including audio-synced output. LTX 2.3 is the first in its line to support native vertical 1080x1920, trained on real portrait data rather than cropped landscape. Prompts accept up to 2,000 characters for detailed scene descriptions.

Is LTX 2.3 free to use?

Yes. New accounts on ltx23.app receive free credits to try AI video generation. After that, you can purchase additional credits or subscribe to a plan to keep creating. Subscription plans offer volume discounts for frequent creators.

Can I use LTX 2.3 outputs commercially?

Yes. Videos generated on ltx23.app include full commercial rights — no watermarks, no royalty fees. The open-source license also permits commercial use of locally generated outputs for qualifying organizations, covering advertising, social media, broadcast, and print.

Which model formats and workflows are available?

LTX 2.3 is available as a base checkpoint, distilled checkpoint with LoRA, FP8 scaled variant, and GGUF quantized format. It integrates directly with ComfyUI for custom workflows including first-and-last-frame control, spatial upscaler, depth conditioning, and IC-LoRA motion tracking. All weights are downloadable from Hugging Face.

How do I get started with LTX 2.3?

Create a free account on ltx23.app, enter a text prompt describing your video, optionally upload a reference image or audio, set parameters like duration and aspect ratio, then click generate. Your video is ready to download in moments — no video editing or AI expertise required.

• Create an account on ltx23.app to access the free credits and start generating videos.
• Choose your generation mode: text-to-video, image-to-video, or audio-to-video.
• Enter a detailed prompt describing your desired scene, ensuring it's under 2,000 characters.
• Select video parameters including duration (4-20 seconds), aspect ratio (16:9, 9:16, 1:1, 4:3), and resolution (up to 1080p).
• Click the generate button and wait for the cloud processing to complete your video.
• Download your finished video, which includes commercial rights and no watermarks.