Generative AI

Building with text, image, audio, and multimodal models

28 chapters across 7 modules

1

The Generative AI Landscape

4 chapters

1

What Generative AI Is, and What It Isn't

6 min read

2

The Family of Generative Models

6 min read

3

Latent Space: The Unifying Idea

7 min read

4

How Generative AI Is Actually Used

6 min read

2

Working With Text Generation

4 chapters

1

Calling a Generative Model

6 min read

2

Controlling the Output

7 min read

3

Structured Generation

7 min read

4

Context Windows & Long Inputs

7 min read

3

Image Generation

5 chapters

1

From Diffusion to Stable Diffusion

7 min read

2

CLIP and Text Conditioning

8 min read

3

Prompting Image Models

7 min read

4

Controlling and Editing Images

8 min read

5

Personalization: LoRA, DreamBooth & Textual Inversion

8 min read

4

Audio Video And Multimodal

4 chapters

1

Speech: TTS and Transcription

7 min read

2

Music & Audio Generation

7 min read

3

Video Generation

7 min read

4

Multimodal Models

6 min read

5

Evaluating Generative Output

3 chapters

1

Why Generative Evaluation Is Hard

7 min read

2

Metrics by Modality

7 min read

3

Human and LLM-as-Judge Evaluation

8 min read

6

Ethics Law And Trust

4 chapters

1

Copyright and Training Data

8 min read

2

Deepfakes, Consent & Misuse

7 min read

3

Provenance and Watermarking

8 min read

4

Bias, Safety Filters & Responsible Deployment

9 min read

7

Building And Shipping Gen AI

4 chapters

1

Architecture of a Gen AI Feature

7 min read

2

Cost, Latency & Scaling

7 min read

3

Capstone: A Multimodal Content Studio

9 min read

4

Where to Go Next

6 min read