https://github.com/zuellni/qt-caption

Image captioning GUI using Florence-2.
https://github.com/zuellni/qt-caption

florence-2 image-captioning pyside6 qt6

Last synced: 4 days ago
JSON representation

Image captioning GUI using Florence-2.

• Host: GitHub
• URL: https://github.com/zuellni/qt-caption
• Owner: Zuellni
• License: mit
• Created: 2024-08-20T11:46:23.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-11-08T16:05:24.000Z (12 days ago)
• Last Synced: 2024-11-08T17:19:30.737Z (12 days ago)
• Topics: florence-2, image-captioning, pyside6, qt6
• Language: Python
• Homepage:
• Size: 2.18 MB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Qt Caption

A simple image captioning GUI using [Florence-2](https://huggingface.co/collections/microsoft/florence-6669f44df0d87d9c3bfb76de).

## Installation

Create a new environment with mamba:

```

mamba create -n qt-caption git python pytorch pytorch-cuda torchvision -c conda-forge -c nvidia -c pytorch

mamba activate qt-caption

```

Clone the repository and install requirements:

```

git clone https://github.com/zuellni/qt-caption

pip install -r qt-caption/requirements.txt

```

## Usage

Start the GUI with:

```

python qt-caption

```

Or with a script like this to hide the console:

```bat

@echo off

call mamba activate qt-caption

start pythonw qt-caption

```

## Preview

![Preview](assets/preview.png)