Generative Models / generative-models

Diffusion and generative models

Autoencoders, VAEs, GANs, normalizing flows, forward noising, reverse denoising, score matching, U-Net, guidance, latent diffusion, and CLIP.

shellbackend needed later
Focus
  • GAN vs VAE vs diffusion
  • noise schedules
  • classifier-free guidance
  • latent diffusion
Future feature idea

GAN/VAE/diffusion comparison with noising, denoising, guidance, latent diffusion, and CLIP conditioning.

Self-check
  1. What is the core job of "Diffusion and generative models"?
  2. Which common mistake would break a production implementation of this topic?
  3. Which inputs or limits must be validated before the interactive feature ships?
  4. What is the smallest test that proves the future implementation behaves correctly?
  5. When does this module really need backend compute, and when is a UI simulation enough?
Implementation notes
  • Start with one focused feature, not a full course inside one page.
  • All public inputs must be typed, bounded, and covered by reject-case tests.
  • If a model, dataset, or job is added, document source, license, limits, and fallback.
  • The interaction must explain the topic rather than serve as decoration.