Pixel art generation using discrete diffusion
Training a small transformer to generate 16x16 pixel art characters by de-masking pixels step by step.
Strayforge on StrayForge
Recent content in Strayforge on StrayForge
Latest posts
Batch, layer, and group norm, side by side on MNIST
A simple MLP on MNIST to see how batch, layer, and group normalization differ in training speed, accuracy, and neuron activations.
Language generation with discrete diffusion
Building a discrete diffusion transformer (DiT) from scratch and training it to generate Shakespeare-like text, one denoising jump at a time.
Guided diffusion explained with 2-D examples
A follow-up to the 2-D diffusion notebook: steering generation with labels, from vanilla conditioning to classifier-free guidance.
Diffusion model explained with simple 2-D dataset
A trimmed, annotated companion to the 2-D diffusion notebook — with an ODE-vs-SDE sampling comparison.