Inspiration
Studies show that the experience for readers is decreasing along with the number of images in books. As an effect, fewer people are inclined to read.
What it does
Image generator apparatus, or IGA, is both a web app and a chrome extension that allows a reader to visualize the text they are reading. On the web app, a user can pick a book from their library which is then opened in our custom pdf reader. As the reader goes from page to page an AI-generated image is shown on the screen representing the text.
How we built it
We used some of the industries leading technologies to create IGA. To generate an image from given text we first need to summarize the input text. This was done by the famous ChatGPT developed by OpenAI. We then took this summarized text and passed it to DALL-E, another AI by OpenAI that generates images off of text input. Once we have our generated image we can insert it into the DOM content of our page and voila we have an AI-generated image.
Challenges we ran into
Due to the nature of our projects API/get requests were naturally a big part. To implement this we had to learn JavaScript async/await keywords, what they do, and how they work. Unbeknownst to us this was a lot more challenging to grasp than we thought.
Accomplishments that we're proud of
We did it! We were able to create a fully working website and chrome extension within 24 hours!
What we learned
Throughout this project, JavaScript was heavily used and we learn that in some situations it can be extremely troublesome to work with. We also learned to use Flask and how to integrate it into our website with HTML.
What's next for Image Generation Apparatus Based on Books
We plan on adding a feature to where users can upload their own PDF's to the site along with adding real-time updating and a scrolling feature to the PDF GUI.
Log in or sign up for Devpost to join the conversation.