Google's Parti Generator Relies on 20 Billion Inputs to Create Photorealistic Images

The model studies 20 billion parameters before generating a final image.

Parti differs fromImagen, a text-to-image generator that Google designed to use diffusion learning.

The model then learns to decode the static to re-create the original image.

As the model improves, it can turn what looks like a series of random dots into an image.

Google isn’t releasing Parti or Imagen to the public because AI data sets carry the risk for bias.

Google says both Parti and Imagen carry bias towardWestern stereotypes.

Google referred to a companyblog postwhen asked to comment on this story.

Parti and Imagen aren’t the only text-to-image models around.