Update README.md

This project automates the generation of UI test cases from video inputs using Google Gemini API for natural language generation. The system extracts frames from a user-uploaded video, identifies UI elements like buttons, and automatically generates detailed and structured test cases.

The workflow consists of:

Video Input: Users upload a video demonstrating UI functionality.
Frame Extraction: The video is processed, and frames are extracted at a specified interval.
Test Case Generation: Based on user-specified UI elements (e.g., buttons or actions), the system generates prompts describing the functionality, preconditions, test steps, expected results, and suggested automated testing tools.
Google Gemini Integration: The Google Gemini API processes these prompts, creating structured and human-readable test cases.
The output includes essential test case details such as:

Button functionality
Preconditions for each button
Step-by-step test procedures
Expected outcomes for each UI element
Recommended tools for automated testing
The Gradio-based interface ensures easy interaction and quick generation of the test cases. This tool streamlines the process of creating high-quality UI test scripts, reducing manual effort and improving efficiency in software quality assurance workflows.

Dependencies:

gradio for building the interface
opencv-python for video processing
google-generativeai for connecting with Google Gemini API

README.md

@@ -1,13 +1,14 @@
 ---
-title: UI-Test Case Generator-MLLM
-emoji: 🦀
-colorFrom: indigo
-colorTo: yellow
+title: Video-to-Test Case Generator with Google Gemini
+emoji: ⚡
+colorFrom: pink
+colorTo: blue
 sdk: gradio
 sdk_version: 4.44.0
 app_file: app.py
 pinned: false
 license: mit
+short_description: Easily generate structured UI test cases by uploading a vide
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference