README.md

metadata

title: TextToImageFlickrSearch
emoji: 🔥
colorFrom: red
colorTo: indigo
sdk: gradio
sdk_version: 4.39.0
app_file: app.py
pinned: false

Project Overview:

In this project, I've combined the CLIP model's advanced image-text matching capabilities with Gradio's user-friendly interface to develop an application that allows users to retrieve and view images from a corpus based on custom text descriptions. Whether you're exploring visual datasets or enhancing search functionality, this tool can be a game-changer!

Key Features:

🔹 CLIP Model Integration: Utilizes OpenAI's pre-trained CLIP model for robust image-text matching.
🔹 Image Corpus Support: Easily integrate and retrieve images from your own directory.
🔹 Interactive Gradio Interface: Provides a seamless experience for inputting text and viewing results.
🔹 Customizable Inputs: Combine dropdown selections and text input for versatile search options.
🔹 Optimized Display: Reduced-size image output for a cleaner and more efficient gallery view.

How It Works:

🔹 User Input: Enter a description in the provided text box.
🔹 Image Retrieval: The application uses the CLIP model to match the description with the most relevant images from the corpus.
🔹 Results Display: The best-matching images are displayed in a gallery for easy viewing.

Check it out on GitHub:

🔗 GitHub Repository[https://github.com/SeemGoel/AIExtensiveVision_/blob/main/Session%2023/README.md]

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference