LightricksLightricks·🎬 Video Generation

LTX Video 2.0 Full Quality

anonymized
Try on Venice.ai ↗
Quick reference
LTX Video 2.0 Full Quality — TLDR
  • - 🆕 Lightricks LTX-2 line: open-weights audio-and-video generation foundation model.
  • - 🧠 DiT-based architecture generating synchronized video and audio in one model.
  • - 🎯 "Full Quality" variant targets high-fidelity, production-grade final renders.
  • - ⚡ Sibling "Fast" variant trades detail for rapid iteration loops.
  • - 📏 LTX-2 line supports resolutions up to 4K with synced audio.
  • - 🔧 Distributed with open weights via Hugging Face.
  • - 🌐 Runs locally from the open release or through Lightricks' API.
  • - 💬 Text-to-video endpoint: prompts drive both visuals and sound.
💰 Pricing
$0.400 – $2.64
per generation
📅 On Venice since
Nov 27, 2024
553 days ago
Provider

Lightricks is a creative technology company founded in January 2013, widely recognized for its popular selfie-editing app Facetune. Originally focused on mobile video and image editing tools, the company has expanded significantly into generative AI,…

Read full profile →
12 models on Venice
12 video
Since Nov 27, 2024

About this model

LTX Video 2.0 Full Quality is the high-fidelity, text-to-video member of Lightricks' LTX-2 family, a DiT-based foundation model that Lightricks describes as generating synchronized video and audio within a single model. Lightricks positions LTX-2 as the open-source successor to its earlier LTX-Video model, releasing it with open weights. Within the lineup, this "Full Quality" tier is meant for final-quality renders, while the companion LTX Video 2.0 Fast favors speed and tight feedback loops.

The generational jump from the original LTX-Video is meaningful in capability terms. The earlier LTX-Video was a DiT model producing roughly 30 FPS clips at 1216×704 resolution. The LTX-2 line, by contrast, adds native audio generation alongside video and targets resolutions up to 4K, making voice, music, and sound effects part of the same generation pass.

For image-conditioned work, the LTX Video 2.0 Full Quality image-to-video variant covers the same fidelity tier. A scaled-up LTX Video 2.0 19B checkpoint also exists in the family.

This is not the newest LTX release: Lightricks subsequently shipped LTX Video 2.3 Full Quality, a more recent open-source update in the LTX line. If your workflow prioritizes the latest checkpoint, the 2.3 line is the more current option.

This About section is AI-generated from public sources (Claude Opus 4.8), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.

Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 1d ago