---
language:
- en
base_model: liuhaotian/llava-v1.6-vicuna-7b
tags:
- retext
- llava
- image-captioning
- person-re-identification
- arxiv:2602.05785
---

<p align="center"><img src="assets/retext-header.png" alt="ReText" width="100%"></p>

<div align="center">

# ReText: Fine-tuned VLM Weights

**LLaVA fine-tuned on UFine3C for person image captioning**

[GitHub](https://github.com/timmzak/ReText) · [Paper (arXiv)](https://arxiv.org/abs/2602.05785) · [Textual annotations](https://huggingface.co/datasets/timmzak/ReText-Captions)

</div>

**Accepted by WACV 2027**

## Overview

This directory contains the fine-tuned VLM weights used to generate textual descriptions for ReText and a script for captioning your own images using HAM.

## Release contents

| File | Description |
| :--- | :--- |
| [ham-release/ham/non_lora_trainables.safetensors](ham-release/ham/non_lora_trainables.safetensors) | Fine-tuned weights loaded on top of the base model. |
| [ham-release/ham/config.json](ham-release/ham/config.json) | Model configuration. |
| [ham-release/caption_own_images.py](ham-release/caption_own_images.py) | Batch caption generation script. |
| [ham-release/requirements.txt](ham-release/requirements.txt) | Python dependencies. |

The base models are not bundled. The script uses `liuhaotian/llava-v1.6-vicuna-7b` and `openai/clip-vit-large-patch14-336` from Hugging Face unless local copies are present under `MODELS_DIR` in directories named `llava-v1.6-vicuna-7b` and `clip-vit-large-patch14-336`.

## Caption your own images

Requirements: Linux, Python 3.10, and an NVIDIA GPU with approximately 16 GB of memory.

### 1. Download the release

Install the Hugging Face Hub client and download the files:

```bash
pip install huggingface_hub
hf download timmzak/ReText-LLaVA --local-dir ReText-LLaVA
cd ReText-LLaVA
```

### 2. Get HAM and the captioning script

Run from the downloaded release directory:

```bash
git clone https://github.com/MPI-Lab/HAM.git
cp ham-release/caption_own_images.py ham-release/requirements.txt HAM/
cd HAM
```

### 3. Create the environment

```bash
python3.10 -m venv ham-env
source ham-env/bin/activate
pip install -r requirements.txt
```

Do not run `pip install -e .` for HAM itself.

### 4. Configure paths

Edit the settings at the top of `caption_own_images.py`:

```python
MODELS_DIR = "/absolute/path/to/ReText-LLaVA/ham-release"
IMAGE_DIR = "/absolute/path/to/images"
OUTPUT_PATH = "captions.jsonl"
```

`MODELS_DIR` must contain the `ham` directory with the weights and configuration. The script also exposes `GPU`, `BATCH_SIZE`, and `NUM_WORKERS` settings.

### 5. Generate captions

```bash
python caption_own_images.py
```

## Output

The script writes a JSONL file with one record per image. Each record has an `image` field containing the path relative to `IMAGE_DIR` and a `caption` field containing the generated description.

Restarting the script with the same output file skips images already recorded there. The captioning prompt can be changed through `PROMPT`; each caption uses a randomly chosen annotator style, as in HAM.

## Citation

```bibtex
@article{mamedov2026retext,
  title={ReText: Text boosts generalization in image-based person re-identification},
  author={Mamedov, Timur and Kvanchiani, Karina and Konushin, Anton and Konushin, Vadim},
  journal={arXiv preprint arXiv:2602.05785},
  year={2026}
}
```