Comify

What it does

Comify takes at least 3 pictures (and up to 9) and both turns the pictures into comics, and creates a story to go along with them!

How we built it

We built this ios app in swift using AWS image recognition. Once given the array of objects from AWS we then selected a Protagonist, Setting, and Adventures from the pictures to create a fantastical adventure for our user. We then also comicfy the pictures they uploaded to make it more comic-booky, more likely to go with the story. We were planning to include natural language processing by having our model create more of the story, so every story would be much more unique, but sadly that could not be implemented into our program before the deadline.

Accomplishments that we're proud of

We're pretty goshdarn proud of the natural language processor, even if it didn't get implemented in time. It uses a corpus of over a million words (1,167,335) to build its n-gram model and predict the next word in a story. We are also proud of getting a functional ios app up and running with AWS.

Built With

Submitted to

MadHacks 2018

Created by

I think I had a pretty important part in the initial planning, though it was definitely Aditya's idea and vision. The main focus of my time was on the natural language generation we wanted to implement, I stayed up all night getting my ngram model to work, and it does! I'm losing confidence we will be able to implement it into the app though as swift seems very hard pressed to make it impossible to launch any other type of program from an ios app.

thenerdjake
I created and debugged the swift file that came up with the story by finding online datasets for things/actions computer vision can recognise. This served as an essential part in basing the theme, setting, character and other features of the story. I also, helped Aditya debug the xCode project.

sarwagya8
Aditya Saxena