CoolFace
Modelpublic

LiconStudio/LTX-2.5-Multiple-Subject-Reference

sourceHugging Faceapache-2.0updated 12h agoView on Hugging Face
79likes10kdownloads
Model Card

<h1 align="center">Licon MSR V1 for LTX-2.5</h1>

<p align="center"> <a href="https://github.com/liconstudio/ComfyUI-LTX2.5-MSR"> <img src="https://img.shields.io/badge/GitHub-Code-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub Code"> </a> <a href="https://arxiv.org/abs/2609.18393"> <img src="https://img.shields.io/badge/arXiv-Paper-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white" alt="arXiv Paper"> </a> </p>

<p align="center"> <a href="https://arxiv.org/abs/2609.18393"> <b>MSR: Multiple Subject Reference for Video Generation</b> </a> </p>

Overview

Licon MSR V1 is a multi-reference LoRA trained for LTX-2.5.

It uses the Multiple Subject Reference (MSR) approach to encode multiple reference images as visual tokens in the same latent space as the target video. Each reference is assigned a learned slot embedding and a distinct negative temporal position, allowing target video tokens to retrieve character, clothing, object, and scene information through the model's native self-attention layers.

Key Features

  • Supports up to five reference images
  • Preserves multiple characters, clothing, objects, and backgrounds
  • Learned slot embeddings distinguish different references
  • Native self-attention retrieval of reference details
  • Supports multi-subject and subject-object composition
  • Designed specifically for the LTX-2.5 architecture

Usage

ComfyUI inference requires [ComfyUI-LTX2.5-MSR](https://github.com/liconstudio/ComfyUI-LTX2.5-MSR). A sample workflow is included in the plugin repository.

Usage Tips

  • Describe each reference image clearly in the prompt.
  • Use consistent labels such as Image 1, Image 2, and Image 3.
  • Clearly specify subject actions and spatial relationships.
  • Specify which reference provides the character, object, clothing, or background.

Examples

<table> <tr> <th align="center">Example 03</th> <th align="center">Example 06</th> <th align="center">Example 07</th> </tr>

<tr> <td align="center">

<b>Reference Images</b><br><br>

<img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/03/01.png" width="100%"><br> <img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/03/02.png" width="100%"><br> <img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validition_V1/03/03.png" width="100%"><br><br>

<video src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/03/MiniMaxH3.mp4" controls width="100%"></video> <br><b>MiniMax H3</b><br><br>

<video src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validition_V1/03/MSR.mp4" controls width="100%"></video> <br><b>Licon MSR V1</b>

</td>

<td align="center">

<b>Reference Images</b><br><br>

<img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/06/01.png" width="100%"><br> <img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/06/02.png" width="100%"><br> <img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validition_V1/06/03.png" width="100%"><br><br>

<video src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/06/MiniMaxH3_no-cut.mp4" controls width="100%"></video> <br><b>MiniMax H3</b><br><br>

<video src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validition_V1/06/MSR-no-cut.mp4" controls width="100%"></video> <br><b>Licon MSR V1</b>

</td>

<td align="center">

<b>Reference Images</b><br><br>

<img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/07/01.png" width="100%"><br> <img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/07/02.png" width="100%"><br> <img src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validition_V1/07/03.png" width="100%"><br><br>

<video src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validitionV1/07/MiniMaxH3.mp4" controls width="100%"></video> <br><b>MiniMax H3</b><br><br>

<video src="https://huggingface.co/LiconStudio/LTX-2.5-Multiple-Subject-Reference/resolve/main/validition_V1/07/MSR.mp4" controls width="100%"></video> <br><b>Licon MSR V1</b>

</td> </tr> </table>