Code for implemeting a conditional DDPM trained on CIFAR10
This code modifies a basic denosing diffusion probailistic model (DDPM) to create a conditional DDPM trained on the CIFAR-10 dataset which is able to generate synthetic images from a combination of different input category labels
-
cifar_ddpm.py - implements and trains conditional ddpm
-
image_generator.py - produces generative images according to input conditions using trained model
Louis Chapo-Saunders