Fablr

Inspiration

The entertainment industry is witnessing a significant shift towards interactive and immersive storytelling experiences. However, converting traditional text-based stories into engaging visual novels remains a time-consuming, labor-intensive, and skill-dependent process.

What it does

Our project is an AI-based application that can automatically convert written stories or prompts into visually appealing and interactive visual novels, reducing the time, effort, and expertise needed for such a transformation.

This is done by asking the user to type in a storyline or prompt. From there, the text inputted is passed into ChatGPT where it outputs paragraphs and corresponding image descriptions of the paragraphs. The image descriptions are then sent to DALL-E where the images for the paragraphs are generated. The app collects all this information and displays them in a nice and neat layout.

How we built it

We built this project using Next.js and Tailwind CSS for front-end appearances and functionalities. Text prompt processing and API handling are done via Flask.

Challenges we ran into

We faced challenges in formatting ChatGPT's output so that it would generate a paragraph with an associated image description. This was a challenge because we had to figure out a text prompt that would get the result we wanted.

Accomplishments that we're proud of

We are very proud of the simplistic and sleek look of our web app. Additionally, we take great pride in the API we've built that handles both processing the output from ChatGPT and the creation of images from the processed output.

What's next for Fablr

We are looking to host this web app with a dedicated domain name. We also are looking into ways users can save a PDF file of the output and share the information with other people.

Built With

• chatgpt
• dall-e
• flask
• next.js
• tailwind