AI Roadmaps
← All roadmaps
IntermediateRoadmap 09 · 12 steps · 9h 21m of video

Generative AI: Images & Video

How machines create images and video: VAEs, GANs, diffusion, latent diffusion, and flow matching.

Before this: Deep Learning.

  1. 20 min
    Step 1

    Variational autoencoders

    Learn a latent space you can sample from.

    Variational Autoencoders | Generative AI Animated

    Deepia

  2. 21 min
    Step 2

    GANs

    A generator and a critic, trained against each other.

    Generative Adversarial Networks (GANs) - Computerphile

    Computerphile

  3. 37 min
    Step 3

    How AI images and videos work

    The best visual explanation of diffusion there is.

    But how do AI images and videos actually work? | Guest video by Welch Labs

    3Blue1Brown

  4. 18 min
    Step 4

    How image generators work

    Noise in, picture out, explained simply.

    How AI Image Generators Work (Stable Diffusion / Dall-E) - Computerphile

    Computerphile

  5. 32 min
    Step 5

    DDPM, animated

    The math of denoising diffusion, made visual.

    Diffusion Models: DDPM | Generative AI Animated

    Deepia

    huggingface/diffusion-models-class★ 4.4k
  6. 31 min
    Step 6

    Diffusion from scratch

    Code and train a small diffusion model in PyTorch.

    Diffusion models from scratch in PyTorch

    DeepFindr

    lucidrains/denoising-diffusion-pytorch★ 10.7k
  7. 13 min
    Step 7

    Latent diffusion

    Why Stable Diffusion works in a compressed space.

    How does Stable Diffusion work? – Latent Diffusion Models EXPLAINED

    AI Coffee Break with Letitia

  8. 17 min
    Step 8

    Stable Diffusion in code

    Run the pipeline piece by piece.

    Stable Diffusion in Code (AI Image Generation) - Computerphile

    Computerphile

    huggingface/diffusers★ 35k
  9. 5h 04m
    Step 9

    Code Stable Diffusion from scratch

    The full model, every component, in PyTorch.

    Coding Stable Diffusion from scratch in PyTorch

    Umar Jamil

  10. 16 min
    Step 10

    Flow matching vs. diffusion

    The newer training recipe behind today's image models.

    Flow-Matching vs Diffusion Models explained side by side

    AI Coffee Break with Letitia

  11. 12 min
    Step 11

    How video generation works

    From images to consistent motion.

    How do AI video generation models work?

    Google for Developers

  12. 39 min
    Step 12

    ComfyUI

    Build image-generation workflows visually.

    How to use ComfyUI for beginners.

    Sebastian Kamph

    Comfy-Org/ComfyUI★ 147.8k

Build it

Watching isn't learning. Pick one and put it on GitHub.

Next roadmap