Skip to content

Latest commit

 

History

History
56 lines (40 loc) · 2.33 KB

readme.md

File metadata and controls

56 lines (40 loc) · 2.33 KB

Image Captioning and Tagging with Google Gemini

Image

This Streamlit app enables users to perform image captioning and tag extraction using the Google Generative AI service. It utilizes Streamlit for the user interface and Google's Generative AI library for image analysis.

Access the Web Version

Explore the app here.

Features

  • Image Upload: Users can upload images in jpg, png, or jpeg formats.
  • Caption Generation: The app generates captions for the uploaded image.
  • Tag Extraction: Extracts hashtags related to the image.
  • Error Handling: Validates user-entered API keys and displays specific error messages.
  • Result Display: View the uploaded image alongside its generated caption and tags.

Usage

  • Clone the repository:
    git clone https://github.com/Sgvkamalakar/ImageTagger
  • Install dependencies:
     pip install -r requirements.txt
  • Run the Streamlit app:
    streamlit run app.py
  • Enter your Google Studio API key when prompted and upload an image for analysis.

Dependencies

  • Python 3.10 or above
  • Streamlit
  • PIL (Python Imaging Library)
  • Google Generative AI library

Why Use This App?

  • Simplicity: Streamlined interface for effortless image analysis.
  • Insightful Information: Obtain concise yet informative captions and tags for images.
  • Versatility: Useful for content creators, marketers, and anyone seeking descriptive insights from images.

This app aims to provide a user-friendly platform harnessing the capabilities of Google Gemini, making image understanding and interpretation accessible to everyone.

Contributions

Contributions are welcome! Fork the repository and create a pull request.

References

CodeSmith harnesses the power of Google's Gemini, a cutting-edge AI model, to achieve efficient code translation and generation across diverse programming languages. Gemini's robust functionalities empower CodeSmith with seamless contextual understanding, facilitating the delivery of precise and accurate results in code translation and generation processes.

Connect with Me

LinkedIn