Home/Generative AI/GAN (Generative Adversarial Network)
Generative AI

GAN (Generative Adversarial Network)

Two networks trained against each other — one faking, one detecting — until the fakes pass. The technique diffusion largely replaced.

Reviewed July 10, 2026Stable
Reading level: Curious
Pick your depth ↓

When not to use it

  • For general image generation today. Diffusion models are better, more diverse, and vastly less painful to train. Choose a GAN only for a specific reason.
  • When you need output diversity. Mode collapse is not an edge case; it's the characteristic failure, and it produces confident sameness.
  • When you can't evaluate by looking. There's no loss value that means "good," and the automated metrics are proxies you shouldn't trust alone.

Reach for something else instead

  • Diffusion models — the default for image generation now: stable training, better coverage of the data distribution.
  • VAEs when you want a well-behaved latent space and can accept blurrier output.
  • Distilled diffusion if what you actually wanted was GAN-like speed with diffusion quality.

A GAN pits a generator against a discriminator until fakes look real.

noise generator discriminator real data fake real?

Two networks train in opposition: the generator makes fake samples from noise, and the discriminator tries to tell real from fake. Each pushes the other — the generator improves to fool the discriminator, the discriminator improves to catch it — and at equilibrium the fakes are indistinguishable from real data. That adversarial game is what produced the first convincingly realistic AI-generated images.

Further reading

  • Goodfellow et al. (2014), Generative Adversarial Nets — the original, and unusually readable.
  • Karras et al. (2018), A Style-Based Generator Architecture for Generative Adversarial Networks — StyleGAN, the peak of GAN image quality.
  • Arjovsky, Chintala & Bottou (2017), Wasserstein GAN — the most influential attempt to make training stable, and a clear account of why it wasn't.

Primary sources, listed so you can check the claims on this page rather than take them on trust.

Where people go wrong

  • Reading a falling generator loss as progress. In an adversarial game, loss values are relative to an opponent that's also moving. They mean much less than they appear to.
  • Fighting mode collapse with more training. It's a failure of the objective, not of patience.
  • Trusting FID as ground truth. It's sensitive to implementation details and rewards things human viewers don't care about.

At a glance

FieldGenerative AI
Core ideagenerator vs. discriminator
Introduced2014, Goodfellow et al.
Strengthsingle-pass speed
Weaknessunstable training, mode collapse
DifficultyAdvanced
Flashcards for this concept · study, save or share them →
Question
Answer
1 / 4

Often compared with

GAN vs. diffusion — one fast pass from an unstable contest vs. many steady steps from a stable objective.

Where this sits

11 concepts come first. Understanding it opens up 1 more.

6Levelsteps in
11Needs firstconcepts
1Opens up0% of 310
2Areascrosses fields
LEARN FIRST Generative AI Loss Function GAN Deepfake UNLOCKS
GAN sits after Generative AI and Loss Function, and leads to 1 concept.

Computed from the prerequisite graph, not assigned. How this works