VideoMakerAI

Automatically create the best animation video from your collection of stock images

Comment

Inspiration:

We love creating fun movies out of the images we photograph, usually during our travel adventures. But, it is always a hassle to come back to import the videos into one of the video editing software, and create the transitions as required, which usually end up becoming highly time-consuming, hence, I am unable to share a short animation on the fly.

So, we came up with the idea to provide a simple AI solution to the user, such that they can create a great simple video with interesting transitions for their images, ready to share instantly.

What It Does:

The application takes in the images through which you want to create a video, and combines them in the best possible ways to get a randomized video created from the combination of the images that you uploaded.

How We Built It:

We used reactjs for the frontend and Django for the backend. The whole part of stitching the parts of image together with the required transitions are done using opencv.

Challenges We Ran Into:

The major challenge we ran into was the whole process of stitching the parts of the image together to get the final video. Our first approach was to use ffmpeg, but there were multiple problems we faced due to the library essentially calling in shell level functions. Therefore, we eventually shifted our focus to using opencv for video processing. We dived deep into the whole process of creating different transitions using images and applying them with best optimizations.

Accompollishments, I am proud of:

This is what we wanted to build for a long time, to use in case of faster video creation times for my travels.

What's next for VideoMakerAI:

We will be working to add more transitions, and create more personalized videos for the different topics that the user can decide while creating the video

Built With: Reactjs, Django, *Opencv

Built With

Share this project:

Updates