50. Diffusion Models

Learning objectives

• Introduce Diffusion Models

• You can add notes on each slide with blocks like this!
• Load a deck in the browser and type “s” to see these notes.

Unsupervised Representation Learning

rooms

modifications to pictures

• image source: Radford, et al, 2016

filters

trained filters

• image source: Radford, et al, 2016

Image Space

vector space of images

• image source: Deep Learning Illustrated

ex1

image space

• image source: Radford, et al, 2016

ex2

image space

• image source: Radford, et al, 2016

Diffusion Models

Diffusion Models

A (denoising) diffusion model isn’t that complex if you compare it to other generative models such as Normalizing Flows, GANs or VAEs: they all convert noise from some simple distribution to a data sample. This is also the case here where a neural network learns to gradually denoise data starting from pure noise.

—HuggingFace

U-net architecture

• image source: HuggingFace