GenAI Foundations
Everything a beginner needs to truly get generative AI — from diffusion and LLMs to your very first creation.
Generative AI turned a keyboard into a film studio, an art department, and a record label. This path explains, in plain language, how models like Imagen 3, Sora 2, and Suno actually work — what they nail, where they fail, and how to use them ethically. You finish by creating your first image in VAR2, step by step.
Lessons in this path
-
What Is Generative AI?
Generative AI creates brand-new images, video, and music instead of just labeling what already exists. Here is what it is — and how it learned to create.
-
How Image Models Work
From pure static to a finished picture in seconds — meet diffusion, the surprisingly simple idea behind modern image models.
-
How LLMs Work
Tokens, next-word prediction, and context windows — the three ideas that explain every chat AI you have ever used.
-
GenAI Vocabulary 101
Fifteen terms, five minutes, zero jargon-panic. Learn the vocabulary that makes every AI tutorial, changelog, and Discord thread suddenly make sense.
-
Capabilities and Limits
An honest map of what 2026 AI models genuinely nail — and where they still faceplant, from hallucinations to melted text.
-
Choosing the Right Model
NanoBanana or Imagen 3? Sora 2 or Veo 3.1? A simple decision framework for picking the right model for images, video, and music — without wasting tokens.
-
AI Ethics and Copyright
Who owns AI art? What is fair game commercially? The training-data debate, deepfake red lines, and disclosure rules — the lesson that keeps you out of trouble.
-
Your First Creation
Enough theory. In the next ten minutes you will generate your first AI image in VAR2 — free tokens, starter prompt, and remix ideas included.