Story Visualizer

This project makes use of 2 LLMs.

1. Text Bison 001 by Google
2. Stable Diffusion

Here, when a user enters a paragraph; the text bison model, summarizes the text, and creates a description of a picture in relation to this paragraph.

This is further sent to the stable diffusion model, which generates the picture.

How to run

Download the source code, and install requirements.

Run the app using this command:

streamlit run main.py

Sample Output