https://github.com/tristan-mcinnis/ollama-image-processing-cli-tool
This tool processes images from a specified directory or file using a local API for image analysis. It allows users to provide custom prompts and select vision-capable models for generating image descriptions.
https://github.com/tristan-mcinnis/ollama-image-processing-cli-tool
ai cli image-annotation image-annotation-tool image-processing local-llm ollama python
Last synced: 7 months ago
JSON representation
This tool processes images from a specified directory or file using a local API for image analysis. It allows users to provide custom prompts and select vision-capable models for generating image descriptions.
- Host: GitHub
- URL: https://github.com/tristan-mcinnis/ollama-image-processing-cli-tool
- Owner: tristan-mcinnis
- Created: 2024-11-26T04:32:28.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-11-26T04:40:06.000Z (10 months ago)
- Last Synced: 2025-01-26T15:29:23.651Z (8 months ago)
- Topics: ai, cli, image-annotation, image-annotation-tool, image-processing, local-llm, ollama, python
- Language: Python
- Homepage:
- Size: 13.7 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Image Processing CLI Tool
This tool processes images from a specified directory or file using a local API for image analysis.
It allows users to provide custom prompts and select vision-capable models for generating image descriptions.
## Features
- Encodes and processes images using a local API.
- Supports various image formats (e.g., JPG, PNG, BMP, TIFF, HEIC).
- Generates image descriptions using user-defined or default prompts.
- Logs detailed progress with categorized feedback.
- Saves results to timestamped output files.
## CLI Showcase
## Installation
1. Clone the repository:
```bash
git clone https://github.com/tristan-mcinnis/Ollama-Image-Processing-CLI-Tool.git
cd Ollama-Image-Processing-CLI-Tool
```
2. Install the required dependencies:
```bash
pip install -r requirements.txt
```
3. Ensure your local API server is running at `http://localhost:11434`.
## Usage
Run the script:
```bash
python main.py
```
### Configuration
1. The default directory for images is `./data`. Create this directory and add your images before running the script.
2. Select a vision-capable model and customize the prompt during runtime.
## Supported Models
Ensure you have a vision-capable model like `llava:latest` installed on your local server.
## Output
Processed results are saved in the `./outputs` directory with timestamped filenames.
## Requirements
- Python 3.8+
- Local API server running at `http://localhost:11434`
## License
MIT License