GAN

Overview

A generative adversarial network trains two models against each other: a generator that produces samples and a discriminator that tries to tell them from real ones. It solves the problem of generating sharp, realistic data without an explicit likelihood. It exists because a learned critic gives a much more useful training signal for images than a per-pixel loss, which tends to produce blur.

Technology Graph

How GAN connects to the rest of the stack.

Alternatives

• Diffusion technique

  An alternative to GAN · source

Comparisons

Side-by-side breakdowns with the alternatives above.

• GAN vs Diffusion