---
base_model: Lightricks/LTX-Video
library_name: ltx
license: other
pipeline_tag: any-to-any
tags:
- id-lora
- ltx-2
- audio-video
- identity-transfer
- lora
---

# ID-LoRA-TalkVid

ID-LoRA (Identity-Driven In-Context LoRA) enables identity-preserving audio–video generation in a single model. This repository contains the ID-LoRA checkpoint trained on the TalkVid dataset.

[**Project Page**](https://id-lora.github.io/) | [**GitHub**](https://github.com/ID-LoRA/ID-LoRA) | [**Paper**](https://huggingface.co/papers/2603.10256)

## Model Description

ID-LoRA jointly generates a subject's appearance and voice in a single model, letting a text prompt, a reference image, and a short audio clip govern both modalities together. Built on top of [LTX-2](https://github.com/Lightricks/LTX-Video), it is the first method to personalize visual appearance and voice within a single generative pass.

Unlike cascaded pipelines that treat audio and video separately, ID-LoRA operates in a unified latent space where a single text prompt can simultaneously dictate the scene's visual content, environmental acoustics, and speaking style—while preserving the subject's vocal identity and visual likeness.

## Details

| Property | Value |
|----------|-------|
| **Base model** | [LTX-2 19B](https://github.com/Lightricks/LTX-Video) |
| **Training dataset** | TalkVid |
| **LoRA rank** | 128 |
| **Training steps** | 6,000 |
| **Strategy** | `audio_ref_only_ic` with negative temporal positions |

## Usage

To use this checkpoint, clone the [official repository](https://github.com/ID-LoRA/ID-LoRA) and run the inference script:

```bash
python scripts/inference_two_stage.py \
  --lora-path lora_weights.safetensors \
  --reference-audio reference_speaker.wav \
  --first-frame first_frame.png \
  --prompt "[VISUAL]: A person speaks in a sunlit park... [SPEECH]: Hello world... [SOUNDS]: ..." \
  --output-dir outputs/
```

## Files

- `lora_weights.safetensors` -- LoRA adapter weights (~1.1 GB)
- `training_config.yaml` -- Training configuration used to produce this checkpoint

## Citation

```bibtex
@misc{dahan2026idloraidentitydrivenaudiovideopersonalization,
  title     = {ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA},
  author    = {Aviad Dahan and Moran Yanuka and Noa Kraicer and Lior Wolf and Raja Giryes},
  year      = {2026},
  eprint    = {2603.10256},
  archivePrefix = {arXiv},
  primaryClass  = {cs.SD},
  url       = {https://arxiv.org/abs/2603.10256}
}
```