SartajBhuvaji / PictureTales

Generating a simple story from an image.

PictureTales

PictureTales allows you to upload an image, and it will generate a short story based on the image's content using image captioning. The generated story is then converted to audio using text-to-speech technology. You can both see the generated story and listen to it.

Demo

• Launching the application

• Select an image and Upload

• Image

• Download the audio story

story.mp4

Features

• Upload an image.
• Generate a story based on the content of the image.
• Listen to the generated story as an audio file.

Usage

1. Clone this repository to your local machine.

git clone https://github.com/SartajBhuvaji/Image-to-Story-Generator.git

pip install -r requirements.txt

python app.py

• Create a .env file and paste your HUGGINGFACE, OPEN AI API Keys (Check the dummy_env file)
• Open your web browser and navigate to http://localhost:7860 to access the app.
• Upload an image to the app and click "Generate Story." You will see the generated story and be able to listen to it as audio.

Tech

• HuggingFace
• Image to Caption model
• Chat GPT 3.5 LLM
• Text-to-speech