Training my own StyleGAN2 Model

latent interpolation video

Objective: Use Runway to train my own StyleGAN2 model using images from Flicker.

I first scraped 3838 images from Flicker using the keyword “coffee”. Then, I uploaded the dataset to Runway. I used StyleGAN2 with Flickr Faces pre-trained model and 3000 steps to train my coffee model. After 5 hours, my model produced a FID 92.01. I suspect the high value is due to limited number of steps and the complexity of the dataset. Pictures in the dataset varied from people with coffee, people without coffee, brewed coffee, to actual coffee beans.

Screenshot of Runway

Here are some of my favorite synthesized images:

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s