https://github.com/imgraywolf/hybrid-image-tagger
Generate accurate image tags with Hybrid Image Tagger, combining WD Tagger and Vision Language Model. Easy to use with Gradio UI. 🌐
https://github.com/imgraywolf/hybrid-image-tagger
ai automation concurrency dataset-preparation gradio image-annotation image-datasets image-tagging llm lora metadata onnxruntime openai prompt python stable-diffusion tagger training
Last synced: 2 months ago
JSON representation
Generate accurate image tags with Hybrid Image Tagger, combining WD Tagger and Vision Language Model. Easy to use with Gradio UI. 🌐
- Host: GitHub
- URL: https://github.com/imgraywolf/hybrid-image-tagger
- Owner: Imgraywolf
- Created: 2025-08-07T04:10:04.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2025-08-08T20:21:52.000Z (2 months ago)
- Last Synced: 2025-08-08T22:19:55.324Z (2 months ago)
- Topics: ai, automation, concurrency, dataset-preparation, gradio, image-annotation, image-datasets, image-tagging, llm, lora, metadata, onnxruntime, openai, prompt, python, stable-diffusion, tagger, training
- Language: Python
- Size: 366 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Hybrid Image Tagger: Automate Image Tagging for AI Projects
 [](https://github.com/Imgraywolf/hybrid-image-tagger/releases)
## Table of Contents
- [Overview](#overview)
- [Features](#features)
- [Installation](#installation)
- [Usage](#usage)
- [Contributing](#contributing)
- [License](#license)
- [Contact](#contact)
## Overview
The **Hybrid Image Tagger** is a powerful tool designed to automatically generate descriptive tags for image datasets. It leverages both WD Tagger and VLM technologies, making it ideal for preparing training data for models like Stable Diffusion and LoRA. With a user-friendly web interface, users can easily manage their image datasets and streamline the tagging process.
## Features
- **Automatic Tag Generation**: Quickly generate relevant tags for images in bulk.
- **User-Friendly Web UI**: Navigate easily through a clean and intuitive interface.
- **Batch Processing**: Handle large datasets efficiently without compromising performance.
- **Concurrency Support**: Process multiple images simultaneously to save time.
- **Integration with Stable Diffusion**: Prepare datasets specifically for AI model training.
- **Support for ONNX Runtime**: Enhance performance with optimized model execution.
- **Metadata Handling**: Manage image metadata seamlessly.
## Installation
To get started with the Hybrid Image Tagger, follow these steps:
1. **Clone the Repository**:
```bash
git clone https://github.com/Imgraywolf/hybrid-image-tagger.git
cd hybrid-image-tagger
```
2. **Install Dependencies**:
Ensure you have Python installed. Then, run:
```bash
pip install -r requirements.txt
```
3. **Download the Latest Release**:
Visit the [Releases section](https://github.com/Imgraywolf/hybrid-image-tagger/releases) to download the latest version. Follow the instructions provided in the release notes to execute the tool.
## Usage
Once installed, you can start using the Hybrid Image Tagger:
1. **Run the Application**:
```bash
python app.py
```
2. **Access the Web UI**:
Open your web browser and go to `http://localhost:5000`.
3. **Upload Images**:
Use the upload feature to select images from your local storage.
4. **Generate Tags**:
Click on the "Generate Tags" button to automatically tag your images.
5. **Download Tagged Dataset**:
Once the tagging is complete, download the dataset directly from the UI.
## Contributing
We welcome contributions to improve the Hybrid Image Tagger. Here’s how you can help:
1. **Fork the Repository**: Create your own copy of the project.
2. **Create a Branch**: Use a descriptive name for your branch.
```bash
git checkout -b feature/your-feature-name
```
3. **Make Changes**: Implement your feature or fix.
4. **Commit Your Changes**:
```bash
git commit -m "Add your message here"
```
5. **Push to Your Fork**:
```bash
git push origin feature/your-feature-name
```
6. **Create a Pull Request**: Submit your changes for review.
## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
## Contact
For questions or feedback, feel free to reach out:
- **Email**: [your.email@example.com](mailto:your.email@example.com)
- **GitHub**: [Imgraywolf](https://github.com/Imgraywolf)
## Topics
- AI
- Automation
- Batch Processing
- Concurrency
- Dataset Preparation
- Gradio
- Image Annotation
- Image Datasets
- Image Tagging
- LLM
- LoRA
- Metadata
- ONNX Runtime
- OpenAI
- Prompt
- Python
- Stable Diffusion
- Tagger
- Training
Explore the capabilities of the Hybrid Image Tagger and enhance your AI projects. For more details and updates, check the [Releases section](https://github.com/Imgraywolf/hybrid-image-tagger/releases).