← Lessons

quiz vs the machine

Platinum1850

Machine Learning

The Diffusion For Images Deep

Learning to reverse gradual noising to generate images.

6 min read · advanced · beat Platinum to climb

Two opposite processes

A diffusion model defines a forward process that slowly adds Gaussian noise to an image over many steps until it is pure noise. Generation learns the reverse process that removes noise step by step to recover a clean image.

What the network predicts

At each step a network, often a UNet, looks at a noisy image and a timestep and predicts the noise that was added. Subtracting a portion of that predicted noise gives a slightly cleaner image. Repeating from pure noise yields a sample.

Why this is stable

Each step is a small, well posed denoising task. Compared to adversarial training, the objective is a simple regression, so training is stable and mode coverage is strong, capturing diverse outputs.

Conditioning and latents

To steer generation, the network is conditioned on text or other signals, often through cross attention. To save compute, latent diffusion runs the whole process in a compressed latent space rather than on raw pixels, then decodes once at the end.

The cost

The main drawback is slow sampling because many denoising steps are needed. Faster samplers and distillation reduce the step count to make generation practical.

Key idea

Diffusion models learn to reverse a gradual noising process by repeatedly predicting and removing noise, giving stable training and diverse samples, with latent space and faster samplers cutting the heavy sampling cost.

Check yourself

Answer to earn rating on the learn ladder.

1. What does the network typically predict at each diffusion step?

2. Why is latent diffusion more efficient?

3. What is the main drawback of diffusion sampling?