---
title: LTX 2.3 Distilled
emoji: 📚
colorFrom: indigo
colorTo: green
sdk: gradio
sdk_version: 6.8.0
python_version: '3.12'
app_file: app.py
pinned: false
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

## Models

`app.py` looks for the models in this order:

1. **Mounted volumes** (recommended): `/models/ltx` (`Lightricks/LTX-2.3`) and
   `/models/gemma` (`google/gemma-3-12b-it-qat-q4_0-unquantized`).
   Attach them once with `python setup_volumes.py <user>/<space>`.
2. The local Hugging Face cache.
3. A download from the Hub (needs a `HF_TOKEN` Space secret for the gated Gemma repo and
   lots of free disk space).

Gemma is gated: accept its license on the model page with the account that owns the token / Space.

Optional Space variables: `LTX_MODEL_DIR`, `GEMMA_MODEL_DIR`, `LTX_REPO_ID`, `GEMMA_REPO_ID`,
`LTX_DISTILLED_FILENAME`, `LTX_UPSCALER_FILENAME`.

See `SETUP_FA.md` for the Persian step-by-step guide.