Macalinao Studio · Self-paced curriculum · 44 lessons

Understand the machines that generate everything.

One curriculum from tokens to transformers to diffusion — every lesson interactive, narrated where it helps, with live playgrounds you can break. Built for creative leads who want the mechanism, not the mystique.

Start Level 01 → See the course map
0
Lessons
0
Levels & tracks
0
Live playgrounds
0
Audio narrations
The route — four levels, then pick a track
01 FOUNDATIONS 5 LESSONS 02 THE TRANSFORMER 6 LESSONS 03 TRAINING A MODEL 7 LESSONS 04 RUNNING MODELS 7 LESSONS T1 IMAGE TRACK 9 LESSONS T2 VIDEO TRACK 5 LESSONS T3 VOICE TRACK 5 LESSONS
01

Words become math.

Tokens, embeddings, and the loss function — the raw material every model is made of.

5 lessons
1A, 1B
02

Inside the transformer.

Attention from first principles, Q/K/V, and the block that stacks into everything.

6 lessons
1C
03

How models learn.

Pretraining at scale, RLHF and the alignment toolbox, LoRA fine-tuning.

7 lessons
1D
04

Models in production.

The decoding loop, KV caches, local engines, RAG, and the chat interfaces on top.

7 lessons
1E, 2
T1

The image track.

ViT, CLIP, diffusion, ControlNet, FLUX — pixels as tokens.

9 lessons
3
T2

The video track.

Temporal diffusion, LTX, persona persistence, audio sync.

5 lessons
4
T3

The voice track.

Whisper STT, codec-LM TTS, voice cloning, live attendants.

5 lessons
5