This Machine Learning art turned into freelance work and teaching. Tools used to create those images are StyleGAN, Google CoLab, Google Drive, After effects, RunwayML, Photoshop.

Instagram, Medium

Very first and still favourite outcome exploring StyleGAN.

Step 1: Creating new shapes and colors

For the first step, I used StyleGAN with a twist. Instead of a big and similar data set usually used, I went for a small, diverse set of images and trained it for a fairly short time. This exploration opened doors to new variations in color and form.

A training progress of 3 datasets using StyleGAN.

Step 2: Feeding the trained dataset back

Next I used the results of my earlier experiments in order to feed them back and train a new model with a more advanced technology using RunwayML.

Step 3: AbstractbyAI by AbstractbyAI: Text to Image

Finally, I utilized a text-to-image tool to generate images in the style of my newly trained dataset. This enabled me to create for example, a "Shanghai Skyline" image in the unique AbstractbyAI aesthetic.

An AbstractbyAI interpretation of "A rapeseed field in Malmö".
"A sunset over Malmö".

What began as personal exploration has evolved into freelance gigs, along with teaching on the side. But overall, it's mainly a passion project, a safe space for me to keep exploring new technologies.

AbstractbyAI during the DEMO festival 2022 in Amsterdam.