LightricksLightricks·video

LTX Video 2.3 Full Quality

Image-to-video
Advertised as fal-ai/ltx-2.3/image-to-videoltx-2-v2-3-full-image-to-video
Quick reference
LTX Video 2.3 Full Quality — TLDR
  • 🆕 Lightricks' LTX Video 2.3, released March 2026.
  • 🎬 Full-quality image-to-video endpoint in the LTX family.
  • 👁️ Image-to-video generation aimed at detailed, stable renders.
  • 🌐 Open-source video model with weights on Hugging Face.
  • ⚡ Sits alongside a Fast variant for quicker iteration.
  • 🔧 Optimized for iterative creative workflows.
💰 Best price on Antseed
$0.039
per second of video · cheapest seller
🐜 Sellers
2
advertising on Antseed
🔬 Model checks
Not audited yet
no audit of this model so far
📏 Context
—
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, developing its own video…

Explore 5 more models by Lightricks →
About this model

LTX Video 2.3 Full Quality is the high-fidelity image-to-video endpoint in Lightricks' LTX 2.3 release, part of an open-source video-generation family. The 2.3 generation, dated March 5, 2026, is split into Fast variants tuned for rapid iteration and Full Quality (Pro) variants intended for more detailed, stable final renders.

As the newest entry in its lineage, this model follows the same-family predecessors LTX Video 2.0 19B from January 2026 and the earlier LTX Video 2.0 Full Quality. It continues Lightricks' approach of pairing open weights with image-to-video workflows, positioned as the quality-focused counterpart to the faster checkpoints in the same release.

Lightricks distributes the LTX 2.3 weights openly on Hugging Face, consistent with the family's open-source orientation. When generation speed matters more than maximum fidelity, this Full Quality variant can be paired with the LTX Video 2.3 Fast sibling, which targets quicker iteration within the same 2.3 generation.

View source on GitHub ↗View model card on HuggingFace ↗
Sources
huggingface.coLightricks/LTX-2.3 · Hugging Face· huggingface.co

This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.

Sellers serving LTX Video 2.3 Full Quality (2)compare on the network explorer →
SellerRep↓SalesVideoRouting$ / s$ / video

"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.