Skip to main content

Ctrl+K

Foundations

Introduction to Generative Models
Neural Networks as Trainable Maps for Imaging
Receptive Fields, U-Nets, and Conditional Image Networks
Random Variables, Latent Variables, and Deep Latent Variable Models
Evaluating Generated Images: FID, KID, and Practical Cautions

Variational Autoencoders

Variational Autoencoders: ELBO, Inference, and Learning
Variational Autoencoder Variants and Extensions

Generative Adversarial Networks

Generative Adversarial Networks
GAN Variants and Modern Practice

Diffusion Models

Discrete Diffusion Models
Score-Based Models, SDEs, and Probability Flow ODEs
Prompted Generation, Classifier-Free Guidance, and Latent Diffusion

Flow Matching

Flow Matching
Flow Matching Variants and Modern Practice

Setup and References

Environment Setup
Further Reading

Repository
Open issue

Index

By Davide Evangelista

© Copyright 2023.