Gemini Image Demo is a Streamlit application that utilizes the Gemini AI model to generate responses based on input prompts and uploaded images. The application allows users to input prompts related to images, upload images, and receive AI-generated responses.
To run the Gemini Image Demo locally, follow these steps:
-
Clone this repository to your local machine:
git clone https://github.com/Jihen-Belhoudi/Visionary-Invoice-Insights-Unveiling-the-Power-of-Gemini-AI
-
Navigate to the project directory:
cd gemini-image-demo
-
Install the required dependencies:
pip install -r requirements.txt
-
Create a
.env
file in the project directory and set your Google API key:GOOGLE_API_KEY=<your-google-api-key>
-
Run the Streamlit application:
streamlit run app.py
-
Access the application in your web browser at
http://localhost:8501
.
- Input a prompt related to the image in the "Input Prompt" field.
- Upload an image by clicking on the "Choose an image..." button.
- Click the "Tell me about the image" button to generate a response based on the input prompt and uploaded image.
- View the generated response below the image.
Gemini AI is a generative AI model developed by Google that leverages state-of-the-art natural language processing and computer vision techniques to generate content based on input prompts and images.
This project is licensed under the MIT License.