https://github.com/iteranya/captioner
Image To Text with Florence 2
https://github.com/iteranya/captioner
ai batch-processing caption-generation florence image-processing image-recognition img2txt
Last synced: 3 months ago
JSON representation
Image To Text with Florence 2
- Host: GitHub
- URL: https://github.com/iteranya/captioner
- Owner: Iteranya
- Created: 2024-12-21T11:42:59.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-12-21T11:50:20.000Z (5 months ago)
- Last Synced: 2024-12-29T07:33:29.564Z (5 months ago)
- Topics: ai, batch-processing, caption-generation, florence, image-processing, image-recognition, img2txt
- Language: Python
- Homepage:
- Size: 9.77 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Image Captioner
Better ones might already exist.
This is made to quickly caption a folder full of images using Florence 2
## How to install
1. Clone the Captioner repository:
```bash
git clone https://github.com/Iteranya/Captioner.git
cd Captioner
```
2. Create a virtual environment:
```bash
python3 -m venv venv
source venv/bin/activate # On Windows, use `venv\Scripts\activate`
```
3. Install Python dependencies:
```bash
python3 -m pip install -r requirements.txt
```
## How To Use
1. Insert images into the images folder
2. Run the bot:
```bash
python main.py
```
3. You can find a txt containing the caption inside the images folder.
## Credits
- Model Used: https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v2.0