LTX Video 2.5 Pro
lightricks/ltx-2.5/text-to-video/proltx-2-5-pro-text-to-video- 🧠 Built on a 22B-parameter asymmetric dual-stream diffusion transformer, per Lightricks.
- 🆕 Pro-tier text-to-video model of the LTX-2.5 open foundation generation.
- 💬 Generates synchronized audio together with video, not silent clips.
- 🎯 Successor to LTX 2.3, adding multi-shot scenes in one pass.
- 🔧 Also supports editing of real footage and cinema-grade EXR export.
- ⚡ Pro tier targets final renders; Fast tier targets quick iteration.
- 🌐 Open foundation model, offered with hosted API access by Lightricks.
- 🏢 From Lightricks, the studio behind the Facetune editing apps.
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 →LTX Video 2.5 Pro is the quality-oriented text-to-video tier of the LTX-2.5 generation from Lightricks, released in 2026. Lightricks' model documentation describes LTX-2.5 as an open foundation model for cinematic creation, built on a 22-billion-parameter asymmetric dual-stream diffusion transformer that produces synchronized audio alongside picture rather than silent footage.
Against its same-family predecessors LTX Video 2.3 Full Quality and LTX Video 2.3 Fast, Lightricks' LTX-2.5 page frames the new generation around several added capabilities: multi-shot scenes generated in a single pass rather than stitched from separate clips, editing of real recorded footage, cinema-grade EXR export for downstream color and compositing work, and rendering compute allocated according to scene complexity.
Within the 2.5 line, the Pro and Fast labels follow Lightricks' own API tiering: the Fast tier is intended for iteration, storyboards and previews, while the Pro tier is aimed at final renders. Users who want cheaper drafts of the same prompt can switch to LTX Video 2.5 Fast; those starting from an existing still image should use LTX Video 2.5 Pro in its image-to-video form, or LTX Video 2.5 Fast for quick image-driven tests.
Lightricks, founded in 2013 and known for its video and image editing apps including Facetune, publishes the LTX models as an open foundation family while also offering hosted generation through its own API, which suits teams that want to prototype on a managed endpoint before self-hosting.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · LTX Video 2.5 Pro · Organic sellers
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| Open Forge 0x1d90…b0aa | healthy | 91.11 | $308.88 | 42.9 min | #1 | $0.12 | — |
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 3.7 h | 86.84 | $101.62 | 24.9 min | #2 | $0.0726 | — |
"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.