Using AI to paint the emotions in Toccata in D minor - Bach

This video was created using three different AIs:

The custom model loads the soundtrack, uses the Bag of Symbolic Fourier Approximation Symbols approach to obtain the features in each song, and then uses a CatBoostRegressor to predict the sentiment of the songs, which essentially outputs 8 different emotions for each song.

Once we predict the sentiment of the songs, we then plug these in into midjourney, using the progress command to let us see how the images are created in real-time.

It is quite interesting to see how some of the images seem to start very similarly, but end up with very different outcomes. It seems that the first 5-8 seconds construct the original image, while the last 5-8 seconds creates all the additional detail and slowly brings up the detail to the desired quality.

The images were later upscaled to 4K using ESRGAN models.

[sberky]

can you make one of these but with happier than ever

[edwardlujan]

Been waiting on the sound of silence for months I'll resign myself that will won't happen😅

[_Diam_nd_]

Do "The only thing I know for real" but every lyric is a AI generated photo

[charlesselix]

READ THIS WHOLE THING:

PRAY FOR ISRAEL. PRAY FOR THE PEACE OF JERUSALEM.
THE LORD JESUS CHRIST DIED FOR YOUR SINS AND ROSE AGAIN FROM THE DEAD. WOULD YOU LIKE TO TAKE YOUR PLACE IN HIS HOUSEHOLD? THEN PLEASE REPENT OF ALL YOUR SINS TODAY AND SURRENDER YOUR ENTIRE LIFE TO THE LORD JESUS CHRIST. NOBODY IS OUT OF THE CANDIDACY FOR BECOMING A CHRISTIAN.

[jadeowenhamblyn]

Extremely hellish and disturbing. Unlike the music.