This Streamlit-based application leverages cutting-edge AI models to offer two main functionalities: Image to Text and Text-to-Image Generation. Users can select between these two modes to either generate descriptive captions for images or create images from textual descriptions.
-
Image Captioning:
- Upload an image or provide an image URL.
- Choose between two captioning models: VIT-GPT2 and BLIP.
- Generate and view image captions.
-
Text-to-Image Generation:
- Enter a descriptive text.
- Generate and view images created from the text.
To run this app, you'll need Python installed on your system, along with the Streamlit library and other dependencies.
-
Clone the Repository:
git clone https://github.com/ConceptualCode/image_captioning_and_generation_system.git
-
Navigate to the App Directory:
cd image_captioning_and_generation_system
-
Install Dependencies:
pip install -r requirements.txt
-
Run the App:
streamlit run app.py
After starting the app, navigate through the sidebar to select between the Image Captioning and Text-to-Image Generation features.
-
For Image Captioning:
- Upload an image or enter an image URL.
- Select the captioning model.
- Click 'Process Image' to view the caption.
-
For Text-to-Image Generation:
- Enter your description in the text box.
- Click 'Generate Image' to view the generated image.
- Streamlit
- Latent Stable Diffusion
- Text to Image
- Image Captioning
- PyTorch
- Transformers
- PIL (Python Imaging Library)
Contributions to this project are welcome! Please fork the repository and submit a pull request with your proposed changes.
For any queries or suggestions, please contact Anthony Soronnadi.