Your next step

Different ways to generate media

Denoising, latents, adversarial training and learned paths.

What you’ll learn

Generation can follow different routes
Recognize that output medium does not uniquely determine the generation method.
About 4 minutes · Open activity
Learn to remove added noise
Identify the training task in a simplified denoising example.
About 4 minutes · Open activity
Generate through successive denoising steps
Recognize the sampling route in a simplified diffusion model.
About 4 minutes · Open activity
Conditioning guides what is generated
Explain how a request can guide a generative process.
About 4 minutes · Open activity
A latent representation is a compact working space
Distinguish a latent representation from final pixels.
About 4 minutes · Open activity
A VAE learns a generative representation
Recognize the encode, sample and decode idea of a variational autoencoder.
About 4 minutes · Open activity
A GAN learns through competing objectives
Distinguish a generator from a discriminator in the training setup.
About 4 minutes · Open activity
Flow matching learns a transformation path
Recognize the idea of learning movement from noise toward data.
About 4 minutes · Open activity
Match the generation story
Match three authored process diagrams to their mechanisms, and explain why a plausible generated scene is not evidence of a real event.
About 5 minutes · Open activity