LTX-Video (Lightricks)
Lightricks' 2B DiT video model. Realtime generation on consumer GPUs (~6s @ H100, 24fps).
LTX-Video (Lightricks) is video generation AI model from Replicate, priced at β¬0.000 per 1M input tokens with a unknown context window.
Pricing
API Integration
Use our OpenAI-compatible API to integrate LTX-Video (Lightricks) into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple β just pass a string
const reply = await rw.run("ltx-video-lightricks", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("ltx-video-lightricks", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("ltx-video-lightricks", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive β Lightricks's LTX-Video (Lightricks)
Lightricks was founded in 2013 by Zeev Farbman (CEO), Yaron Inger, Itai Tsiddon, Nir Pochter and Amit Goldstein, spinning out of Hebrew University of Jerusalem's computer-graphics research group. The company is best known for the consumer photo and video apps Facetune, Videoleap, Photoleap and Filtertune, which together have hundreds of millions of installs. Lightricks raised more than $300M from Insight Partners, Goldman Sachs and others, at a $1.8B valuation. In November 2024 Lightricks open-sourced LTX-Video, a 2B-parameter real-time video diffusion model optimized for speed on consumer hardware. LTX-Video positioned the company as one of the few Western players shipping open-weight video AI, and is now embedded in the Videoleap and LTX Studio products.
Visit Lightricks βLTX-Video is a 2B-parameter Diffusion Transformer designed for real-time-ish inference: at launch it generated 5-second 768x512 videos in under 4 seconds on a single H100, and 30-frame clips faster than real time. The architecture compresses video aggressively into a 1:192 spatio-temporal latent (vs the 1:48 typical of HunyuanVideo) using a heavy 3D causal VAE; the DiT denoiser then operates on this very compact latent grid. Position information uses 3D RoPE, and the model is trained with Flow Matching using v-prediction. Text conditioning combines a CLIP-style encoder and a Llama-class LLM encoder. LTX-Video supports text-to-video and image-to-video, with a 'mid-conditioning' mode that allows inserting an intermediate frame for guided motion. The model is published under an open licence designed to enable both research and commercial use.
- Parameters
- 2 billion
- Context
- unknown
- Real-time-class generation: ~5s clip in ~4s on H100 at 768x512
- Open-weight 2B-parameter DiT model
- Text-to-video and image-to-video
- Mid-frame conditioning for guided motion
- Aggressive spatial-temporal compression (1:192 latent)
- Runs on a single 24-48 GB consumer GPU with optimisations
- Apache-style permissive licence on weights
- Active community ecosystem on Hugging Face and ComfyUI
- Best for: interactive creative tools, on-device pipelines, prototyping.
Curated multi-million-clip dataset filtered for aesthetics, motion and caption alignment, with dense captions produced by a vision-language model.
License: Open weights under a permissive licence (research and commercial use with attribution).
Known limitations
- Resolution capped at 768x512 in the base model
- Short native duration (~5s)
- No audio
- Aggressive compression can cause loss of fine detail and text
- Smaller parameter count than Mochi / Hunyuan limits absolute quality
Research papers
Frequently asked questions
Related Models
View all Video GenerationGoogle Veo 2
Google's state-of-the-art video generation model. Simulates real-world physics with various visual styles.
Google Veo 3
Google's Veo 3. High-fidelity text-to-video with native audio generation, up to 8s clips.
Google Veo 3.1
Latest Veo with image-to-video and context-aware audio
Kling v3
Cinematic video up to 15s with multi-shot and native audio
Start using LTX-Video (Lightricks) today
Get started with free credits. No credit card required. Access LTX-Video (Lightricks) and 100+ other models through a single API.