How does AI draw pictures?
Diffusion models add noise to learn, then remove it to create, steered by a prompt.
Transcript
Diffusion models learn by watching pictures being destroyed. Step by step, noise is added, until only static is left.
At every step, the model is shown the noisy image, and asked to predict the noise that was added.
To generate, we run it in reverse. Start from pure random noise.
The model removes a little noise at each step, and a picture slowly emerges.
A text prompt steers the denoising. The words are turned into embeddings, which guide every step.
Different noise gives a different picture, even for the same prompt.
Add noise to learn. Remove noise to create. Guided by your words, static turns into an image.
More in this series
1:14How does AI work?
Neurons and weights, learning from mistakes, and predicting the next word.
1:13How does AI read a sentence?
Tokens, embeddings and attention, stacked in layers to score the next token.
1:17What are billions of parameters?
What a parameter is, how big a billion is, and why big models need racks of GPUs.
1:26How do networks learn from errors?
Loss as a landscape, gradient descent and backpropagation.
1:24How is a chatbot trained?
Pretraining, fine-tuning and human feedback turn a text predictor into an assistant.
1:23What does temperature do?
Scores become probabilities, and temperature sharpens or flattens them.
1:15How can AI use your own documents?
Retrieval-augmented generation: embed, retrieve, augment the prompt, generate.
1:14Why does AI make things up?
Likely is not the same as true: gaps, snowballing errors, and what helps.
1:16How much can an AI remember?
The context window, forgetting, the cost of long inputs, and workarounds.
1:09What is an AI agent?
A model in a loop with tools and guardrails.
1:12Can AI be biased?
Skewed data, where bias comes from, proxies, and how to audit and fix it.
1:10What is overfitting?
Underfit, good fit and overfit curves, train vs test error, and the fixes.