LTX-2-19b-LoRA-TEAR
Released by oumoumad in 2026, LTX-2-19b-LoRA-TEAR is a 19 billion parameter image-generation model. LTX-2-19b-LoRA-TEAR is an open-weights image model with roughly 19 billion parameters.
by oumoumad · 19B parameters
Best for
Ways to use LTX-2-19b-LoRA-TEAR in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your oumoumad API key. osFoundry discovers LTX-2-19b-LoRA-TEAR automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
LTX-2-19b-LoRA-TEAR is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run LTX-2-19b-LoRA-TEAR
LTX-2-19b-LoRA-TEAR runs on a single 16GB consumer GPU (~12 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~46 GB).
LTX-2-19b-LoRA-TEAR vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about LTX-2-19b-LoRA-TEAR
Is LTX-2-19b-LoRA-TEAR free to use?
LTX-2-19b-LoRA-TEAR is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use LTX-2-19b-LoRA-TEAR commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does LTX-2-19b-LoRA-TEAR need?
Approximately 12 GB at Q4 quantisation, or 46 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run LTX-2-19b-LoRA-TEAR locally?
Yes. LTX-2-19b-LoRA-TEAR is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is LTX-2-19b-LoRA-TEAR best at?
LTX-2-19b-LoRA-TEAR is well-suited to image text to video.
How do I use LTX-2-19b-LoRA-TEAR in osFoundry?
Paste your oumoumad API key in the key dialog (or deploy the open weights for self-hostable models), assign LTX-2-19b-LoRA-TEAR to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by oumoumad on January 7, 2026. Source: https://huggingface.co/oumoumad/LTX-2-19b-LoRA-TEAR