---
language: en
license: other
tags:
  - text-to-video
  - ltx-2
  - fp8
  - comfyui
---

# LTX-2 19B Dev FP8 + Gemma encoder

**Organization:** [WindstormLabs](https://huggingface.co/WindstormLabs)  
**Used by:** [SceneMachine](https://huggingface.co/SceneMachine)

SceneMachine is a sub-project of Windstorm Labs. This repo hosts shared AI/ML infrastructure used by SceneMachine and reusable by future Windstorm Labs sub-projects.

## What this is

Lightricks LTX-2 19B Dev FP8 weights plus the Gemma text encoder (sharded 5 files). SceneMachine's alternate cinematic path. Reusable by other Windstorm sub-projects.

## Upstream source

Primary distribution: https://huggingface.co/Lightricks/LTX-2

This repo is a **mirror**. License terms of the upstream apply unchanged.

**Primary license owner(s):** Lightricks (LTX-2 community license) + Google (Gemma Terms of Use)

## Files

| Filename | Size |
|---|---|
| `ltx-2-19b-dev-fp8.safetensors` | 27.08 GB |
| `model-00001-of-00005.safetensors` | 4.98 GB |
| `model-00003-of-00005.safetensors` | 4.93 GB |
| `model-00004-of-00005.safetensors` | 4.93 GB |
| `model-00002-of-00005.safetensors` | 4.93 GB |
| `model-00005-of-00005.safetensors` | 4.60 GB |

**Total: 51.45 GB**

## Related repos

- The full SceneMachine model stack: search the [SceneMachine HF collection](https://huggingface.co/SceneMachine).
- Shared encoders and Wan VAE: [`WindstormLabs/wan22-encoders`](https://huggingface.co/WindstormLabs/wan22-encoders).
- Speed LoRAs: [`WindstormLabs/wan22-loras`](https://huggingface.co/WindstormLabs/wan22-loras).

## Provenance

Mirror created 2026-05-13 from local working copy on the SceneMachine development rig. Hashes preserved via HF's content-addressed storage.

🤖 Repo and README generated by [Claude Code](https://claude.com/claude-code) during a SceneMachine CTO session.